{ "data": { "a": { "slug": "inkling-2-small", "name": "Inkling 2 Small", "vendor": "Thinking Machines Lab", "vendorUrl": "https://thinkingmachines.ai", "kind": "weights", "category": "open-weights", "summary": "Inkling 2 Small is Thinking Machines Lab's open-weight mixture-of-experts model, 594B total and 17B active parameters, taking text and images and returning text, with adjustable thinking effort, published in NVFP4 and MXFP8 under Apache 2.0.", "url": "https://www.anchorterminal.com/tools/inkling-2-small", "markdownUrl": "https://www.anchorterminal.com/tools/inkling-2-small.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/inkling-2-small.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/inkling-2-small.json", "dns": "inkling-2-small.grade.anchorterminal.com", "repo": "https://huggingface.co/thinkingmachines/Inkling-2-Small", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "thinkingmachines/Inkling-2-Small" }, { "registry": "huggingface", "name": "thinkingmachines/Inkling-2-Small-MXFP8" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. Neither repository is gated (checked 2026-11-12). Thinking Machines' Model Acceptable Use Policy, linked from the card, says that downloading or using the weights binds you to it.", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0 with Thinking Machines' Model Acceptable Use Policy on top. Running it yourself costs the hardware, 393.5 GB of files for the NVFP4 checkpoint and 622.8 GB for MXFP8, which Thinking Machines puts at 500 GB and 800 GB of GPU memory. Thinking Machines' Tinker serves it as a beta serverless inference API at $0.30 per million input tokens, $0.03 cached and $1.00 output (read 2026-11-06).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-11-12).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-12" }, "docsUrl": "https://thinkingmachines.ai/model-card/inkling-2-small/", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "moe", "multimodal", "vision", "reasoning", "tool-calling", "apache-2.0", "safetensors", "nvfp4", "self-hosted", "new" ], "lastRelease": "2026-11-12", "graded": true, "anchor": { "graded": true, "score": 58.8, "grade": "C", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1524, "categoryRank": 78, "methodology": "0.8", "run": "2026-10-01", "scores": { "interface": 85, "reach": 40, "risk": 65, "upkeep": 67 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-12" }, "negative": 0, "verdict": "Thinking Machines' newest open model, a 594B mixture-of-experts generalist with images in, several tool calls a turn and per-request thinking effort. The NVFP4 checkpoint needs about 472 GB, and no released runtime runs it yet, so today that means vLLM's or SGLang's own images, or Tinker and Together hosted. The use policy binds on download and can change.", "bestFor": "Teams with 512 GB or more of datacentre GPU memory who want Thinking Machines' newest open multimodal agent model and can run a runtime's pre-release image.", "strengths": [ "Safetensors only, with a checksum on every LFS file in the publisher's own organisation", "Thinking effort set per request from none to xhigh, several tool calls a turn and a 1M-token context", "Two checkpoints from Thinking Machines, NVFP4 and MXFP8, under Apache 2.0 with no gate", "Thinking Machines' tml-renderers package renders prompts and parses tool calls for this model", "A training-content summary with sources, mix and an October 2026 collection cut-off", "Thinking Machines' own Tinker hosts it as beta serverless inference, and the card names seven more API providers" ], "weaknesses": [ "The smaller checkpoint needs about 472 GB, and Thinking Machines says 500 GB of GPU memory", "No released version of vLLM, SGLang, Transformers, llama.cpp or Ollama runs it on 12 November 2026", "Apache 2.0 comes with an acceptable use policy that binds on download and can change at any time", "Safety results are Thinking Machines' own, with no harness to rerun them and no prompt-injection guidance", "Structured output isn't documented, and the card gives no dated knowledge cut-off", "No independent benchmark results were read, so Capability is pending and the total is capped at 61" ], "agentNotes": [ "No released runtime runs it yet. Serve the NVFP4 checkpoint from SGLang's dev-inkling-2-small image with the cookbook's recipe for your hardware, or from vLLM's vllm/vllm-openai:inkling-2-small image", "In vLLM pass `--reasoning-parser inkling --enable-auto-tool-choice --tool-call-parser inkling`. In SGLang the tool-call parser is `inkling2` and the reasoning parser `inkling`", "Transformers' main branch loads only thinkingmachines/Inkling-2-Small-MXFP8, the 622.8 GB checkpoint, and no release has the code yet", "Pass `reasoning_effort` as none, minimal, low, medium, high (the default), xhigh or max, or a number from 0 to 0.99", "Effort none conditions the model toward no reasoning but doesn't forbid it, and higher effort needs a larger max_tokens", "Tool call arguments must reach the template as an object, not a JSON string, or it raises an error", "Images should be 40 to 4096 px a side. The model takes no audio, and the template raises an error for an audio part", "Use guided decoding or validate JSON yourself, since structured output isn't documented", "Without the hardware, call it on Tinker's OpenAI-compatible endpoint with a Tinker key, at $0.30 input and $1.00 output per million tokens as read on 6 November 2026", "Read the Model Acceptable Use Policy before deploying, it binds on download and bars some uses that are legal" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.8", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 58.8 } ], "editorialScores": { "interface": 85, "reach": 40, "risk": 65, "upkeep": 67 }, "provenanceScore": 72, "checked": { "categories": { "interface": "2026-11-12", "reach": "2026-11-12", "risk": "2026-11-12", "upkeep": "2026-11-12" }, "last": "2026-11-12", "lastMoved": "2026-11-12", "oldest": "2026-11-12", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "# per SGLang's cookbook, the NVFP4 checkpoint on 4 B300 GPUs. Not in an SGLang release yet,\n# so run it inside the lmsysorg/sglang:dev-inkling-2-small image:\nSGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK=4096 sglang serve \\\n --model-path thinkingmachines/Inkling-2-Small --tp 4 --ep 4 \\\n --moe-a2a-backend megamoe --attention-backend fa4 --bf16-gemm-backend torch --dtype bfloat16 \\\n --page-size 128 --grammar-backend xgrammar --enable-multimodal \\\n --reasoning-parser inkling --tool-call-parser inkling2", "http": "curl http://localhost:30000/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"model\": \"thinkingmachines/Inkling-2-Small\",\n \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}],\n \"reasoning_effort\": \"low\"\n }'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/inkling-2-small" }, "sameCompany": [ "inkling", "inkling-small" ], "sameModel": [ "tinker" ], "weights": { "trainedBy": "Thinking Machines Lab", "params": "594B", "active": "17B", "context": 1048576, "goodFor": "Mixture-of-experts generalist for coding, agents and tool use with images in, a 1M-token context and thinking effort set per request.", "runtimes": [], "builds": [ { "name": "Inkling-2-Small", "url": "https://huggingface.co/thinkingmachines/Inkling-2-Small", "who": "publisher", "precision": "nvfp4", "sizeGB": 393.5, "memoryGB": 512, "format": "safetensors", "note": "The main checkpoint, in the precision the model was trained in. Routed experts in NVFP4 for layers 0 to 39 and MXFP8 for layers 40 to 47, per SGLang's cookbook. Thinking Machines states at least 500 GB of GPU memory" }, { "name": "Inkling-2-Small-MXFP8", "url": "https://huggingface.co/thinkingmachines/Inkling-2-Small-MXFP8", "who": "publisher", "precision": "mxfp8", "sizeGB": 622.8, "memoryGB": 1024, "format": "safetensors", "note": "Every routed expert in MXFP8. Thinking Machines states at least 800 GB of GPU memory and recommends the NVFP4 checkpoint. It's the only checkpoint Transformers' main branch loads" } ], "run": "SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK=4096 sglang serve --model-path thinkingmachines/Inkling-2-Small --tp 4 --ep 4 --moe-a2a-backend megamoe --attention-backend fa4 --bf16-gemm-backend torch --dtype bfloat16 --page-size 128 --grammar-backend xgrammar --enable-multimodal --reasoning-parser inkling --tool-call-parser inkling2", "runBuild": "Inkling-2-Small", "checked": "2026-11-12", "minMemoryGB": 512 }, "family": { "lab": "Thinking Machines Lab", "family": "Inkling 2", "url": "https://www.anchorterminal.com/open-weights/#thinking-machines" }, "area": "models", "provenance": { "legalEntity": "Thinking Machines Lab, Inc. (named as provider on its model card page and in its training-content summary)", "domain": "thinkingmachines.ai", "domainRegistered": "", "domainNote": "Not looked up: RDAP isn't requested under the 1 November 2026 rules.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/thinkingmachines/Inkling-2-Small/commits/main", "securityTxt": "valid", "checked": "2026-11-12", "notes": [ "Thinking Machines' model card page links both repositories in the thinkingmachines organisation on Hugging Face, which isn't verified by Hugging Face.", "Nothing is hosted for this listing, so the Apache 2.0 licence and the Model Acceptable Use Policy stand in for terms of service and no privacy policy is scored.", "The changelog is the repository's commit history, 3 commits on 12 November 2026, the upload, a library tag from a merged pull request and a card update.", "thinkingmachines.ai/.well-known/security.txt gives a security contact, a PGP key and an expiry in 2029, read on 12 November 2026, and the model card page links a coordinated vulnerability disclosure policy.", "Thinking Machines' terms bar scraping the Services. The founder decided on 6 November 2026 that reading at a person's pace is fine, so six pages were read one at a time on 12 November: the acceptable use policy, the training data page and its summary for this model, the model card page, and the tml-renderers and thinking effort guides. thinkingmachines.ai's robots.txt has no rules, and tinker-docs.thinkingmachines.ai answers 404 for robots.txt." ], "score": 72 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/inkling-2-small.json", "live": { "slug": "inkling-2-small", "probe": { "target": "https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1", "method": "get", "lastAt": "2026-11-13T20:11:37.236512439Z", "lastOk": true, "lastStatus": 404, "lastMs": 439, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 238, "p95ms24h": 467, "samples24h": 245, "samples30d": 1854, "days": [ { "date": "2026-11-06", "probes": 186, "ok": 186 }, { "date": "2026-11-07", "probes": 243, "ok": 243 }, { "date": "2026-11-08", "probes": 243, "ok": 243 }, { "date": "2026-11-09", "probes": 243, "ok": 243 }, { "date": "2026-11-10", "probes": 244, "ok": 244 }, { "date": "2026-11-11", "probes": 244, "ok": 244 }, { "date": "2026-11-12", "probes": 245, "ok": 245 }, { "date": "2026-11-13", "probes": 206, "ok": 206 } ], "since": "2026-11-06T00:00:00Z" }, "securityTxt": { "url": "https://thinkingmachines.ai/.well-known/security.txt", "state": "valid", "expires": "2029-07-13T07:00:00.000Z", "checkedAt": "2026-11-14T16:19:22.779006645Z" }, "llmsTxt": { "url": "https://tinker-docs.thinkingmachines.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-13T15:54:36.79283015Z" }, "domain": { "domain": "thinkingmachines.ai", "registered": "2024-07-09", "source": "https://rdap.identitydigital.services/rdap/domain/thinkingmachines.ai", "checkedAt": "2026-11-08T15:05:10.558189316Z" }, "pages": [ { "url": "https://huggingface.co/thinkingmachines/Inkling-2-Small/commits/main", "kind": "changelog", "status": 200, "checkedAt": "2026-11-14T19:07:35.812797752Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "39971da7a686" }, { "url": "https://tinker-docs.thinkingmachines.ai/changelog/", "kind": "changelog", "status": 200, "checkedAt": "2026-11-13T18:32:58.088087394Z", "changedAt": "2026-11-13T18:32:58.088087394Z", "fingerprint": "c56006412e95" }, { "url": "https://thinkingmachines.ai/legal/privacy/", "kind": "privacy", "status": 200, "checkedAt": "2026-11-13T18:32:53.884197991Z", "changedAt": "2026-11-06T13:43:40.660240815Z", "fingerprint": "3c33a4a74c61" }, { "url": "https://thinkingmachines.ai/legal/terms/", "kind": "terms", "status": 200, "checkedAt": "2026-11-13T18:32:56.034092745Z", "changedAt": "2026-11-06T13:43:42.918165055Z", "fingerprint": "08c6ceca5dbb" } ], "updatedAt": "2026-11-14T19:07:35.812797752Z" }, "streak": { "days": 9, "from": "2026-11-06", "sinceWatching": true, "best": 9 } }, "answer": "Kimi K3 scores 62.4 (B) on agent readiness against Inkling 2 Small's 58.8 (C), and leads in 1 of 4 scored categories. Inkling 2 Small leads on agent interface and documentation and upkeep.", "b": { "slug": "kimi-k3", "name": "Kimi K3", "vendor": "Moonshot AI", "vendorUrl": "https://www.moonshot.ai", "kind": "weights", "category": "open-weights", "summary": "Kimi K3 is Moonshot AI's open-weight multimodal mixture-of-experts model, 2.8T parameters with 104B active and a 1M-token context, trained in MXFP4 and published on Hugging Face under the modified-MIT Kimi K3 Licence.", "url": "https://www.anchorterminal.com/tools/kimi-k3", "markdownUrl": "https://www.anchorterminal.com/tools/kimi-k3.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/kimi-k3.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/kimi-k3.json", "dns": "kimi-k3.grade.anchorterminal.com", "repo": "https://huggingface.co/moonshotai/Kimi-K3", "license": "Kimi K3 License (modified MIT)", "transports": [], "packages": [ { "registry": "huggingface", "name": "moonshotai/Kimi-K3" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository is not gated (checked 2026-10-24).", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under the Kimi K3 Licence. A company running a model-as-a-service business with more than $20 million in revenue over 12 months needs a separate agreement with Moonshot AI, at a price not published. Running it yourself costs the hardware, 1,561 GB of files (checked 2026-10-24).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-10-24).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-02" }, "docsUrl": "https://huggingface.co/moonshotai/Kimi-K3", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "moe", "multimodal", "reasoning", "tool-calling", "modified-mit", "safetensors", "mxfp4", "self-hosted" ], "lastRelease": "2026-09-02", "graded": true, "anchor": { "graded": true, "score": 62.4, "grade": "B", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1524, "categoryRank": 23, "methodology": "0.8", "run": "2026-10-01", "scores": { "capability": 75, "interface": 65, "reach": 50, "risk": 65, "upkeep": 41 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-11-02" }, "negative": 0, "verdict": "Kimi K3 is a 2.8T multimodal agent model with a 1M-token context, parallel tool calls and per-request effort, for long coding and research sessions. Its 1,561 GB of files need a multi-node GPU cluster, so most agents will call a hosted copy. The main risks are Moonshot's Python running at load and prompt time, and no answers in its repository.", "bestFor": "Teams with a multi-node GPU cluster who want an open 1M-context agent model for long coding and research work", "strengths": [ "1,048,576 tokens of context trained in, with indexed parallel tool calls in one turn", "Model code in released vLLM, SGLang and llama.cpp, with recipes linked from the card", "A third-party cyber evaluation by the UK AI Security Institute and CAISI", "Safetensors only, with a SHA-256 for every shard, downloadable with no account", "Served by Moonshot's API and five inference providers for agents without the hardware" ], "weaknesses": [ "1,561 GB of files at its smallest publisher build, far beyond any single machine", "No Jinja template, so prompts, tokeniser and model load through Moonshot's Python with trust_remote_code", "No Moonshot reply in the 40 most recent discussions, and a tokeniser report waits unanswered", "No disclosure route for flaws and no prompt-injection guidance", "No training sources, sizes or knowledge cut-off, and the card leaves out limitations and languages" ], "agentNotes": [ "Start it with SGLang on a node of 8 B300s, sglang serve --trust-remote-code --model-path moonshotai/Kimi-K3 --tp-size 8 --context-length 65536 --mem-fraction-static 0.82 --reasoning-parser kimi_k3 --tool-call-parser kimi_k3 --port 30000", "Use the kimi_k3 tool-call and reasoning parsers in vLLM or SGLang, and validate tool-call arguments against the schema, since vLLM's recipe says K3 sometimes emits a format its parser doesn't expect", "Pass the whole assistant message back every turn, reasoning_content and tool_calls included, or output becomes unstable", "Thinking is always on; set reasoning_effort to low or high when max is too slow", "Sampling per the card is temperature 1.0, with top-p 0.95 for single-step tasks and 1.0 for agentic ones", "Don't hand an ongoing session from another model to K3, and state boundaries in the system prompt, since Moonshot warns it can act on its own when intent is unclear", "Without the hardware, call it through Moonshot's API or an inference provider listed on its Hugging Face page" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.3, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "B", "methodology": "0.8", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 62.4 } ], "editorialScores": { "capability": 75, "interface": 65, "reach": 50, "risk": 65, "upkeep": 41 }, "provenanceScore": 70, "checked": { "categories": { "capability": "2026-11-02", "interface": "2026-11-02", "reach": "2026-11-02", "risk": "2026-11-02", "upkeep": "2026-11-02" }, "last": "2026-11-02", "oldest": "2026-11-02", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "# SGLang, per its Kimi-K3 cookbook linked from the card (one node of 8 B300 GPUs)\nsglang serve --trust-remote-code --model-path moonshotai/Kimi-K3 --tp-size 8 \\\n --context-length 65536 --mem-fraction-static 0.82 \\\n --reasoning-parser kimi_k3 --tool-call-parser kimi_k3 --port 30000\n# or, with llama.cpp and Unsloth's GGUF, a third party's conversion:\nllama-server -hf unsloth/Kimi-K3-GGUF:UD-Q4_K_XL --jinja", "http": "curl http://localhost:30000/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"model\": \"moonshotai/Kimi-K3\",\n \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}],\n \"reasoning_effort\": \"high\"\n }'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/kimi-k3" }, "sameCompany": [ "kimi-code-cli", "kimi-k3-1-pro" ], "weights": { "trainedBy": "Moonshot AI", "params": "2.8T", "active": "104B", "context": 1048576, "goodFor": "Large multimodal agent model for coding and long tool-calling sessions, text and images in, with always-on reasoning and JSON Schema output.", "runtimes": [ "llama.cpp", "vLLM", "SGLang" ], "builds": [ { "name": "Kimi-K3", "url": "https://huggingface.co/moonshotai/Kimi-K3", "who": "publisher", "precision": "mxfp4", "sizeGB": 1560.9, "memoryGB": 2048, "format": "safetensors", "note": "Trained in MXFP4; the only build Moonshot publishes" }, { "name": "unsloth Kimi-K3-GGUF (UD-Q4_K_XL)", "url": "https://huggingface.co/unsloth/Kimi-K3-GGUF", "who": "unsloth", "precision": "q4_k_xl", "sizeGB": 1509.57, "memoryGB": 2048, "format": "gguf", "runsOn": [ "llama.cpp" ], "note": "From Unsloth, a third party's conversion and not Moonshot's. 1508.67 GB of UD-Q4_K_XL weights plus the 0.90 GB F16 projector, from the Hub's model information on 10 November 2026. Recorded after the last grading, so Reach doesn't count it" } ], "run": "sglang serve --trust-remote-code --model-path moonshotai/Kimi-K3 --tp-size 8 --context-length 65536 --mem-fraction-static 0.82 --reasoning-parser kimi_k3 --tool-call-parser kimi_k3 --port 30000", "runBuild": "Kimi-K3", "checked": "2026-10-24", "minMemoryGB": 2048 }, "family": { "lab": "Moonshot AI (Kimi)", "family": "Kimi K3", "url": "https://www.anchorterminal.com/open-weights/#moonshot", "olderCount": 18, "unrestrictedCopies": 5 }, "area": "models", "provenance": { "legalEntity": "Moonshot AI (the licence names Moonshot AI; the Kimi Platform terms name Moonshot AI PTE. LTD.)", "domain": "moonshot.ai", "domainRegistered": "2017-12-15", "domainNote": "The .ai registry's RDAP server (Identity Digital) gives moonshot.ai a registration date of 15 December 2017, read 24 October 2026; rdap.org didn't answer on 21 October.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/moonshotai/Kimi-K3/commits/main", "securityTxt": "none", "checked": "2026-10-24", "notes": [ "The licence names Moonshot AI. The Kimi Platform's terms (platform.kimi.ai/docs/agreement/modeluse) name Moonshot AI PTE. LTD. as the party for its API.", "Nothing is hosted, so the Kimi K3 Licence stands in for terms of service and no privacy policy is scored.", "The changelog is the repository's commit history. Its messages mostly say \"Update README.md\" or \"Update encoding_k3.py\" without saying what changed; the last change, on 2 September 2026, added an evaluation result.", "moonshot.ai, www.moonshot.ai, kimi.com and www.kimi.com answered /.well-known/security.txt with an HTML page and platform.kimi.ai with 404 on 21 and 24 October 2026, so no security.txt was found. The Kimi-K3 GitHub repository has no SECURITY.md." ], "score": 70 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/kimi-k3.json", "live": { "slug": "kimi-k3", "securityTxt": { "url": "https://moonshot.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-14T16:17:32.723243749Z" }, "domain": { "domain": "moonshot.ai", "registered": "2017-12-15", "source": "https://rdap.identitydigital.services/rdap/domain/moonshot.ai", "checkedAt": "2026-11-08T14:52:29.297019771Z" }, "pages": [ { "url": "https://huggingface.co/moonshotai/Kimi-K3/commits/main", "kind": "changelog", "status": 200, "checkedAt": "2026-11-14T19:06:38.030866732Z", "changedAt": "2026-11-14T19:06:38.030866732Z", "fingerprint": "d2d976b15c0d" } ], "updatedAt": "2026-11-14T19:06:38.030866732Z" } }, "edges": [ { "by": 26, "category": "upkeep", "leads": "inkling-2-small", "name": "Documentation and upkeep", "reasons": { "a": "Model card 17 of 20, everything but a dated knowledge cut-off. Training data 15, an EU training-content summary with sources, mix, an October 2026 collection cut-off and filtering. Last change 20, the files were uploaded on 12 November 2026. Responsiveness 0, the repository has no questions yet, which reads as none answered. Version policy 5, a first release. File health 10, the files agree and no broken-file report waits. 17 + 15 + 20 + 0 + 5 + 10 = 67.", "b": "The model card earns 11, covering intended use, architecture, parameters and context, but not limitations, languages or a knowledge cut-off. Training data earns 5 for a general description with no cut-off. The last change earns 15, an encoding_k3.py update on 20 August, 74 days before 2 November and within 90; the GitHub repository's last commit is 6 August. Responsiveness earns nothing, with no Moonshot reply in the 40 most recent discussions. Version policy earns 5 for a first release. File health earns 5, because a report that the tokeniser goes past the declared vocabulary waits without a reply." }, "scores": { "a": 67, "b": 41 } }, { "by": 20, "category": "interface", "leads": "inkling-2-small", "name": "Agent interface", "reasons": { "a": "Chat template 20, a Jinja file in the repository. Tool-calling format 25, Thinking Machines' tml-renderers guide shows how tools are declared and how calls come back for this model, and its package ships the parser. Trained tool calling 20, several calls in one turn. Structured output 0, not documented. Reasoning control 10, thinking effort is set per request from none to xhigh, and the reasoning comes back in reasoning_content. Context 10, up to 1M tokens. 20 + 25 + 20 + 0 + 10 + 10 = 85.", "b": "The chat template earns 10, because there is no Jinja template and the prompt format exists only as encoding_k3.py, code you run. The tool-calling format earns 10, since Moonshot documents the tools channel but the parser name comes only from vLLM's and SGLang's own recipes. Trained tool calling earns 20 for indexed parallel calls in one turn. Structured output earns 5, as the card names it among its linked guides without saying how to ask the weights for it, and the how sits in hosted-API docs. Reasoning control earns 10, with per-request effort documented on the card and reasoning returned as reasoning_content. Context earns 10 for 1,048,576 tokens trained in." }, "scores": { "a": 85, "b": 65 } }, { "by": 10, "category": "reach", "leads": "kimi-k3", "name": "Reach", "reasons": { "a": "Memory 0 of 30, the smallest build is Thinking Machines' NVFP4 checkpoint at 393.5 GB, about 472 GB with a fifth added, above the 256 GB line. Runtimes 0, no released version of the six runs it; vLLM and SGLang serve it from their own images and Transformers has it on its main branch only. Builds 15, two precisions from the publisher (NVFP4 and MXFP8). Terms 10, Apache 2.0 with a binding acceptable use policy on top, read as a custom licence. Download 10, no gate. Hosted 5, Thinking Machines' own Tinker serves it as beta serverless inference, and Together is live on Hugging Face. 0 + 0 + 15 + 10 + 10 + 5 = 40.", "b": "Memory earns nothing, because the only build of 4-bit precision or better from Moonshot or a runtime's own library is Moonshot's MXFP4 release of 1,561 GB, about 1,873 GB with the fifth added, far above 256 GB. Ollama and LM Studio list it only as a cloud model. Runtimes earn 15, for model code in released vLLM, SGLang and llama.cpp; Transformers has no kimi_k3 code of its own and loads Moonshot's remote code, so it doesn't count. Builds earn 10 for one publisher precision, the MXFP4 files the model was trained for. Terms earn 10, a custom MIT-based licence that is free for commercial use below a revenue threshold. Download earns 10, with no gate and no account. Hosted earns 5, since Moonshot's API serves it and five inference providers are live for it on Hugging Face." }, "scores": { "a": 40, "b": 50 } } ], "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Thinking Machines Lab", "b": "Moonshot AI", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "Kimi K3 License (modified MIT)", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-11-12", "b": "2026-09-02", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "none", "b": "2.3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Kimi K3 scores 62.4 (B) on agent readiness against Inkling 2 Small's 58.8 (C), and leads in 1 of 4 scored categories. Inkling 2 Small leads on agent interface and documentation and upkeep.", "question": "Which is better for AI agents, Inkling 2 Small or Kimi K3?" } ], "goodFor": [ { "aheadOn": [ "Agent interface, 85 against 65", "Documentation and upkeep, 67 against 41" ], "also": null, "goodFor": "Teams with 512 GB or more of datacentre GPU memory who want Thinking Machines' newest open multimodal agent model and can run a runtime's pre-release image.", "slug": "inkling-2-small", "watchFor": "The smaller checkpoint needs about 472 GB, and Thinking Machines says 500 GB of GPU memory" }, { "aheadOn": [ "Reach, 50 against 40" ], "also": null, "goodFor": "Teams with a multi-node GPU cluster who want an open 1M-context agent model for long coding and research work", "slug": "kimi-k3", "watchFor": "1,561 GB of files at its smallest publisher build, far beyond any single machine" } ], "history": { "inkling-2-small": [ { "causes": [ "product" ], "date": "2026-11-12", "delta": 6.7, "from": 52.1, "fromGrade": "D", "to": 58.8, "toGrade": "C" } ], "kimi-k3": null }, "job": { "capability": "model.open-weights", "name": "Open-weight models you run yourself" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-inkling-2-small.json", "title": "Agents-A1-4B vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-kimi-k3.json", "title": "Agents-A1-4B vs Kimi K3", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-inkling-2-small.json", "title": "Apertus v1.5 8B vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-kimi-k3.json", "title": "Apertus v1.5 8B vs Kimi K3", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-inkling-2-small.json", "title": "Apodex-1.1-mini vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-kimi-k3.json", "title": "Apodex-1.1-mini vs Kimi K3", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/arete-27b-vs-inkling-2-small.json", "title": "Arete-27B vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/arete-27b-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/arete-27b-vs-kimi-k3.json", "title": "Arete-27B vs Kimi K3", "url": "https://www.anchorterminal.com/compare/arete-27b-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-inkling-2-small.json", "title": "BigBang-v1 vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-kimi-k3.json", "title": "BigBang-v1 vs Kimi K3", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-inkling-2-small.json", "title": "Carbon-X vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-kimi-k3.json", "title": "Carbon-X vs Kimi K3", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/cola2-vs-inkling-2-small.json", "title": "Cola2 vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/cola2-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/cola2-vs-kimi-k3.json", "title": "Cola2 vs Kimi K3", "url": "https://www.anchorterminal.com/compare/cola2-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-inkling-2-small.json", "title": "Cosmos-Reason2-2B vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-kimi-k3.json", "title": "Cosmos-Reason2-2B vs Kimi K3", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-inkling-2-small.json", "title": "Darwin-36B-Opus vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-kimi-k3.json", "title": "Darwin-36B-Opus vs Kimi K3", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling-2-small.json", "title": "DeepSeek-V3.2 vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-kimi-k3.json", "title": "DeepSeek-V3.2 vs Kimi K3", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-inkling-2-small.json", "title": "DeepSeek V4.1 Flash vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-kimi-k3.json", "title": "DeepSeek V4.1 Flash vs Kimi K3", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-inkling-2-small.json", "title": "DeepSeek-V4-Flash-0731 vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-kimi-k3.json", "title": "DeepSeek-V4-Flash-0731 vs Kimi K3", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling-2-small.json", "title": "Devstral Small 2 vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-kimi-k3.json", "title": "Devstral Small 2 vs Kimi K3", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling-2-small.json", "title": "DiffusionGemma 26B A4B IT vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-kimi-k3.json", "title": "DiffusionGemma 26B A4B IT vs Kimi K3", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-inkling-2-small.json", "title": "EXAONE 4.5 33B vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-kimi-k3.json", "title": "EXAONE 4.5 33B vs Kimi K3", "url": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-inkling-2-small.json", "title": "Gemma 4 12B IT vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-kimi-k3.json", "title": "Gemma 4 12B IT vs Kimi K3", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-inkling-2-small.json", "title": "Gemma 4 26B A4B IT vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-kimi-k3.json", "title": "Gemma 4 26B A4B IT vs Kimi K3", "url": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-inkling-2-small.json", "title": "Gemma 4 31B IT vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-kimi-k3.json", "title": "Gemma 4 31B IT vs Kimi K3", "url": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-inkling-2-small.json", "title": "Gemma 4 E2B IT vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-kimi-k3.json", "title": "Gemma 4 E2B IT vs Kimi K3", "url": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-inkling-2-small.json", "title": "Gemma 4 E4B IT vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-kimi-k3.json", "title": "Gemma 4 E4B IT vs Kimi K3", "url": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-inkling-2-small.json", "title": "GLM-4.5-Air vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-kimi-k3.json", "title": "GLM-4.5-Air vs Kimi K3", "url": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-inkling-2-small.json", "title": "GLM-4.7-Flash vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-kimi-k3.json", "title": "GLM-4.7-Flash vs Kimi K3", "url": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling-2-small.json", "title": "GLM-5.3-Flash vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-kimi-k3.json", "title": "GLM-5.3-Flash vs Kimi K3", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-inkling-2-small.json", "title": "GLM-5.3 vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-kimi-k3.json", "title": "GLM-5.3 vs Kimi K3", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-inkling-2-small.json", "title": "gpt-oss-120b vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-kimi-k3.json", "title": "gpt-oss-120b vs Kimi K3", "url": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling-2-small.json", "title": "gpt-oss-20b vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-kimi-k3.json", "title": "gpt-oss-20b vs Kimi K3", "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-30b-vs-inkling-2-small.json", "title": "Granite 4.2 30B vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/granite-4-2-30b-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-30b-vs-kimi-k3.json", "title": "Granite 4.2 30B vs Kimi K3", "url": "https://www.anchorterminal.com/compare/granite-4-2-30b-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-inkling-2-small.json", "title": "Granite 4.2 3B vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-kimi-k3.json", "title": "Granite 4.2 3B vs Kimi K3", "url": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-8b-vs-inkling-2-small.json", "title": "Granite 4.2 8B vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/granite-4-2-8b-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-8b-vs-kimi-k3.json", "title": "Granite 4.2 8B vs Kimi K3", "url": "https://www.anchorterminal.com/compare/granite-4-2-8b-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-inkling-2-small.json", "title": "Hy-Memory-30B-A3B vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-kimi-k3.json", "title": "Hy-Memory-30B-A3B vs Kimi K3", "url": "https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-inkling-2-small.json", "title": "Hy3 vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/hy3-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-kimi-k3.json", "title": "Hy3 vs Kimi K3", "url": "https://www.anchorterminal.com/compare/hy3-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-inkling-small.json", "title": "Inkling 2 Small vs Inkling-Small", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-inkling-small" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-internvl3-5-gpt-oss-20b-a4b-preview.json", "title": "Inkling 2 Small vs InternVL3.5-GPT-OSS-20B-A4B-Preview", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-internvl3-5-gpt-oss-20b-a4b-preview" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3-1-pro.json", "title": "Inkling 2 Small vs Kimi K3.1 Pro", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3-1-pro" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kolibri-1.json", "title": "Inkling 2 Small vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kronos.json", "title": "Inkling 2 Small vs Kronos", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kronos" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-laguna-m-1.json", "title": "Inkling 2 Small vs Laguna M.1", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-laguna-m-1" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-laguna-s-2-1.json", "title": "Inkling 2 Small vs Laguna S 2.1", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-laguna-s-2-1" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-laguna-xs-2-1.json", "title": "Inkling 2 Small vs Laguna XS 2.1", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-laguna-xs-2-1" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lbs-27b.json", "title": "Inkling 2 Small vs LBS-27B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm2-5-2-6b.json", "title": "Inkling 2 Small vs LFM2.5-2.6B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm2-5-2-6b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-1-7b.json", "title": "Inkling 2 Small vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-audio-2b.json", "title": "Inkling 2 Small vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-omni-2b.json", "title": "Inkling 2 Small vs LFM3-Omni-2B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-omni-2b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-vl-2b.json", "title": "Inkling 2 Small vs LFM3-VL-2B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ling-3-0-tiny.json", "title": "Inkling 2 Small vs Ling-3.0-tiny", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ling-3-0-tiny" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ling-3-1-flash-1019.json", "title": "Inkling 2 Small vs Ling-3.1-flash-1019", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ling-3-1-flash-1019" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-longcat-2-5.json", "title": "Inkling 2 Small vs LongCat-2.5", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-longcat-2-5" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-mimo-v2-6-distill-qwen-9b.json", "title": "Inkling 2 Small vs MiMo-V2.6 Distill Qwen 9B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-mimo-v2-6-distill-qwen-9b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-mimo-v2-6-flash-rl.json", "title": "Inkling 2 Small vs MiMo-V2.6-Flash-RL", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-mimo-v2-6-flash-rl" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm-o-4-5.json", "title": "Inkling 2 Small vs MiniCPM-o 4.5", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm-o-4-5" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm-v-4-7-1b.json", "title": "Inkling 2 Small vs MiniCPM-V 4.7 1B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm-v-4-7-1b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm-v-4-7-35b-a3b.json", "title": "Inkling 2 Small vs MiniCPM-V 4.7 35B-A3B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm-v-4-7-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm5-2b.json", "title": "Inkling 2 Small vs MiniCPM5-2B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm5-2b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m2-5.json", "title": "Inkling 2 Small vs MiniMax-M2.5", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m2-5" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m2-7.json", "title": "Inkling 2 Small vs MiniMax-M2.7", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m2-7" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m3-1-flash.json", "title": "Inkling 2 Small vs MiniMax-M3.1-Flash", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m3-1-flash" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-mistral-large-4.json", "title": "Inkling 2 Small vs Mistral Large 4", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-mistral-large-4" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-glimmer-30b.json", "title": "Inkling 2 Small vs Muse Glimmer 30B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-glimmer-30b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nanbeige-4-2-3b.json", "title": "Inkling 2 Small vs Nanbeige4.2-3B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nanbeige-4-2-3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nanbeige-4-3-33b.json", "title": "Inkling 2 Small vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-bolt-e4b-4gb.json", "title": "Inkling 2 Small vs NVIDIA Nemotron 3.5 Bolt E4B 4GB", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-bolt-e4b-4gb" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-lightning-30b-a3b.json", "title": "Inkling 2 Small vs Nemotron 3.5 Lightning 30B A3B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-lightning-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-nano-30b-a3b.json", "title": "Inkling 2 Small vs Nemotron 3 Nano 30B A3B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-nano-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-nano-4b.json", "title": "Inkling 2 Small vs Nemotron 3 Nano 4B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-nano-4b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "Inkling 2 Small vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-super-120b-a12b.json", "title": "Inkling 2 Small vs Nemotron 3 Super 120B A12B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-super-120b-a12b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-ultra-550b-a55b.json", "title": "Inkling 2 Small vs Nemotron 3 Ultra 550B A55B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-ultra-550b-a55b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-north-mini-code-1-0.json", "title": "Inkling 2 Small vs North Mini Code 1.0", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-north-mini-code-1-0" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-occamy-1-0.json", "title": "Inkling 2 Small vs occamy-1.0", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-occamy-1-0" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-olmo-3-7b-think.json", "title": "Inkling 2 Small vs Olmo 3 7B Think", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-olmo-3-7b-think" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-122b.json", "title": "Inkling 2 Small vs Ornith-1.5-122B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-122b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-35b-a3b.json", "title": "Inkling 2 Small vs Ornith-1.5-35B-A3B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-397b.json", "title": "Inkling 2 Small vs Ornith-1.5-397B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-397b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-9b.json", "title": "Inkling 2 Small vs Ornith-1.5-9B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-9b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-otel-2-0-llm-31b-it.json", "title": "Inkling 2 Small vs OTel-2.0-LLM-31B-IT", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-otel-2-0-llm-31b-it" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen-agentworld-35b-a3b.json", "title": "Inkling 2 Small vs Qwen-AgentWorld-35B-A3B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen-agentworld-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-30b-a3b-instruct-2507.json", "title": "Inkling 2 Small vs Qwen3-30B-A3B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-30b-a3b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-4b-instruct-2507.json", "title": "Inkling 2 Small vs Qwen3-4B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-4b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-0-8b.json", "title": "Inkling 2 Small vs Qwen3.5-0.8B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-0-8b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-122b-a10b.json", "title": "Inkling 2 Small vs Qwen3.5-122B-A10B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-122b-a10b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-2b.json", "title": "Inkling 2 Small vs Qwen3.5-2B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-2b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-397b-a17b.json", "title": "Inkling 2 Small vs Qwen3.5-397B-A17B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-397b-a17b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-4b.json", "title": "Inkling 2 Small vs Qwen3.5-4B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-4b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-9b.json", "title": "Inkling 2 Small vs Qwen3.5-9B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-9b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-6-27b.json", "title": "Inkling 2 Small vs Qwen3.6-27B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-6-27b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-6-35b-a3b.json", "title": "Inkling 2 Small vs Qwen3.6-35B-A3B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-6-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-8-27b.json", "title": "Inkling 2 Small vs Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-8-flash-next.json", "title": "Inkling 2 Small vs Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-coder-30b-a3b-instruct.json", "title": "Inkling 2 Small vs Qwen3-Coder-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-coder-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-coder-next.json", "title": "Inkling 2 Small vs Qwen3-Coder-Next", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-coder-next" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-omni-30b-a3b-instruct.json", "title": "Inkling 2 Small vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-2b-instruct.json", "title": "Inkling 2 Small vs Qwen3-VL-2B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-2b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-30b-a3b-instruct.json", "title": "Inkling 2 Small vs Qwen3-VL-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-32b-instruct.json", "title": "Inkling 2 Small vs Qwen3-VL-32B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-32b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-4b-instruct.json", "title": "Inkling 2 Small vs Qwen3-VL-4B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-4b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-8b-instruct.json", "title": "Inkling 2 Small vs Qwen3-VL-8B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-8b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwopus3-8-27b-flash-v2.json", "title": "Inkling 2 Small vs Qwopus3.8-27B-Flash-V2", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwopus3-8-27b-flash-v2" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-recursive-flint.json", "title": "Inkling 2 Small vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ripple-65b-preview.json", "title": "Inkling 2 Small vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-sensenova-loop-9b-preview.json", "title": "Inkling 2 Small vs SenseNova-Loop-9B-Preview", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-sensenova-loop-9b-preview" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-smollm3-3b.json", "title": "Inkling 2 Small vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-spark-x2-6-4b.json", "title": "Inkling 2 Small vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-step-3-7-flash.json", "title": "Inkling 2 Small vs Step 3.7 Flash", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-step-3-7-flash" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-swift-1-5-qwen3-8-27b.json", "title": "Inkling 2 Small vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-swift-1-5-qwen3-8-flash-next.json", "title": "Inkling 2 Small vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-thinkingcap-qwen3-8-27b.json", "title": "Inkling 2 Small vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-thinkingcap-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-unlimited-ocr-2.json", "title": "Inkling 2 Small vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-wevisone-vl-2b.json", "title": "Inkling 2 Small vs WeVisOne-VL-2B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-wevisone-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-wevisone-vl-4b.json", "title": "Inkling 2 Small vs WeVisOne-VL-4B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-wevisone-vl-4b" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-zaya1-8b.json", "title": "Inkling 2 Small vs ZAYA1-8B", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-zaya1-8b" }, { "json": "https://www.anchorterminal.com/compare/inkling-small-vs-kimi-k3.json", "title": "Inkling-Small vs Kimi K3", "url": "https://www.anchorterminal.com/compare/inkling-small-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-inkling-2-small.json", "title": "Inkling vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/inkling-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-kimi-k3.json", "title": "Inkling vs Kimi K3", "url": "https://www.anchorterminal.com/compare/inkling-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-kimi-k3.json", "title": "InternVL3.5-GPT-OSS-20B-A4B-Preview vs Kimi K3", "url": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-kimi-k3-1-pro.json", "title": "Kimi K3 vs Kimi K3.1 Pro", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-kimi-k3-1-pro" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-kolibri-1.json", "title": "Kimi K3 vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-kronos.json", "title": "Kimi K3 vs Kronos", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-kronos" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-laguna-m-1.json", "title": "Kimi K3 vs Laguna M.1", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-laguna-m-1" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-laguna-s-2-1.json", "title": "Kimi K3 vs Laguna S 2.1", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-laguna-s-2-1" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-laguna-xs-2-1.json", "title": "Kimi K3 vs Laguna XS 2.1", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-laguna-xs-2-1" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-lbs-27b.json", "title": "Kimi K3 vs LBS-27B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-lfm2-5-2-6b.json", "title": "Kimi K3 vs LFM2.5-2.6B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-lfm2-5-2-6b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-lfm3-1-7b.json", "title": "Kimi K3 vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-lfm3-audio-2b.json", "title": "Kimi K3 vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-lfm3-omni-2b.json", "title": "Kimi K3 vs LFM3-Omni-2B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-lfm3-omni-2b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-lfm3-vl-2b.json", "title": "Kimi K3 vs LFM3-VL-2B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-lfm3-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-ling-3-0-tiny.json", "title": "Kimi K3 vs Ling-3.0-tiny", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-ling-3-0-tiny" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-ling-3-1-flash-1019.json", "title": "Kimi K3 vs Ling-3.1-flash-1019", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-ling-3-1-flash-1019" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-longcat-2-5.json", "title": "Kimi K3 vs LongCat-2.5", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-longcat-2-5" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-mimo-v2-6-distill-qwen-9b.json", "title": "Kimi K3 vs MiMo-V2.6 Distill Qwen 9B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-mimo-v2-6-distill-qwen-9b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-mimo-v2-6-flash-rl.json", "title": "Kimi K3 vs MiMo-V2.6-Flash-RL", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-mimo-v2-6-flash-rl" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-minicpm-o-4-5.json", "title": "Kimi K3 vs MiniCPM-o 4.5", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-minicpm-o-4-5" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-minicpm-v-4-7-1b.json", "title": "Kimi K3 vs MiniCPM-V 4.7 1B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-minicpm-v-4-7-1b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-minicpm-v-4-7-35b-a3b.json", "title": "Kimi K3 vs MiniCPM-V 4.7 35B-A3B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-minicpm-v-4-7-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-minicpm5-2b.json", "title": "Kimi K3 vs MiniCPM5-2B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-minicpm5-2b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-minimax-m2-5.json", "title": "Kimi K3 vs MiniMax-M2.5", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-minimax-m2-5" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-minimax-m2-7.json", "title": "Kimi K3 vs MiniMax-M2.7", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-minimax-m2-7" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-minimax-m3-1-flash.json", "title": "Kimi K3 vs MiniMax-M3.1-Flash", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-minimax-m3-1-flash" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-mistral-large-4.json", "title": "Kimi K3 vs Mistral Large 4", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-mistral-large-4" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-muse-glimmer-30b.json", "title": "Kimi K3 vs Muse Glimmer 30B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-muse-glimmer-30b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-nanbeige-4-2-3b.json", "title": "Kimi K3 vs Nanbeige4.2-3B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-nanbeige-4-2-3b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-nanbeige-4-3-33b.json", "title": "Kimi K3 vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-5-bolt-e4b-4gb.json", "title": "Kimi K3 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-5-bolt-e4b-4gb" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-5-lightning-30b-a3b.json", "title": "Kimi K3 vs Nemotron 3.5 Lightning 30B A3B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-5-lightning-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-nano-30b-a3b.json", "title": "Kimi K3 vs Nemotron 3 Nano 30B A3B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-nano-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-nano-4b.json", "title": "Kimi K3 vs Nemotron 3 Nano 4B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-nano-4b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "Kimi K3 vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-super-120b-a12b.json", "title": "Kimi K3 vs Nemotron 3 Super 120B A12B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-super-120b-a12b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-ultra-550b-a55b.json", "title": "Kimi K3 vs Nemotron 3 Ultra 550B A55B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-ultra-550b-a55b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-north-mini-code-1-0.json", "title": "Kimi K3 vs North Mini Code 1.0", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-north-mini-code-1-0" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-occamy-1-0.json", "title": "Kimi K3 vs occamy-1.0", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-occamy-1-0" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-olmo-3-7b-think.json", "title": "Kimi K3 vs Olmo 3 7B Think", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-olmo-3-7b-think" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-ornith-1-5-122b.json", "title": "Kimi K3 vs Ornith-1.5-122B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-ornith-1-5-122b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-ornith-1-5-35b-a3b.json", "title": "Kimi K3 vs Ornith-1.5-35B-A3B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-ornith-1-5-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-ornith-1-5-397b.json", "title": "Kimi K3 vs Ornith-1.5-397B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-ornith-1-5-397b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-ornith-1-5-9b.json", "title": "Kimi K3 vs Ornith-1.5-9B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-ornith-1-5-9b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-otel-2-0-llm-31b-it.json", "title": "Kimi K3 vs OTel-2.0-LLM-31B-IT", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-otel-2-0-llm-31b-it" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen-agentworld-35b-a3b.json", "title": "Kimi K3 vs Qwen-AgentWorld-35B-A3B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen-agentworld-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-30b-a3b-instruct-2507.json", "title": "Kimi K3 vs Qwen3-30B-A3B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-30b-a3b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-4b-instruct-2507.json", "title": "Kimi K3 vs Qwen3-4B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-4b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-5-0-8b.json", "title": "Kimi K3 vs Qwen3.5-0.8B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-5-0-8b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-5-122b-a10b.json", "title": "Kimi K3 vs Qwen3.5-122B-A10B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-5-122b-a10b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-5-2b.json", "title": "Kimi K3 vs Qwen3.5-2B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-5-2b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-5-397b-a17b.json", "title": "Kimi K3 vs Qwen3.5-397B-A17B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-5-397b-a17b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-5-4b.json", "title": "Kimi K3 vs Qwen3.5-4B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-5-4b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-5-9b.json", "title": "Kimi K3 vs Qwen3.5-9B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-5-9b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-6-27b.json", "title": "Kimi K3 vs Qwen3.6-27B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-6-27b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-6-35b-a3b.json", "title": "Kimi K3 vs Qwen3.6-35B-A3B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-6-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-8-27b.json", "title": "Kimi K3 vs Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-8-flash-next.json", "title": "Kimi K3 vs Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-coder-30b-a3b-instruct.json", "title": "Kimi K3 vs Qwen3-Coder-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-coder-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-coder-next.json", "title": "Kimi K3 vs Qwen3-Coder-Next", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-coder-next" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-omni-30b-a3b-instruct.json", "title": "Kimi K3 vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-vl-2b-instruct.json", "title": "Kimi K3 vs Qwen3-VL-2B-Instruct", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-vl-2b-instruct" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-vl-30b-a3b-instruct.json", "title": "Kimi K3 vs Qwen3-VL-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-vl-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-vl-32b-instruct.json", "title": "Kimi K3 vs Qwen3-VL-32B-Instruct", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-vl-32b-instruct" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-vl-4b-instruct.json", "title": "Kimi K3 vs Qwen3-VL-4B-Instruct", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-vl-4b-instruct" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-vl-8b-instruct.json", "title": "Kimi K3 vs Qwen3-VL-8B-Instruct", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-vl-8b-instruct" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwopus3-8-27b-flash-v2.json", "title": "Kimi K3 vs Qwopus3.8-27B-Flash-V2", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-qwopus3-8-27b-flash-v2" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-recursive-flint.json", "title": "Kimi K3 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-ripple-65b-preview.json", "title": "Kimi K3 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-sensenova-loop-9b-preview.json", "title": "Kimi K3 vs SenseNova-Loop-9B-Preview", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-sensenova-loop-9b-preview" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-smollm3-3b.json", "title": "Kimi K3 vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-spark-x2-6-4b.json", "title": "Kimi K3 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-step-3-7-flash.json", "title": "Kimi K3 vs Step 3.7 Flash", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-step-3-7-flash" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-swift-1-5-qwen3-8-27b.json", "title": "Kimi K3 vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-swift-1-5-qwen3-8-flash-next.json", "title": "Kimi K3 vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-thinkingcap-qwen3-8-27b.json", "title": "Kimi K3 vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-thinkingcap-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-unlimited-ocr-2.json", "title": "Kimi K3 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-wevisone-vl-2b.json", "title": "Kimi K3 vs WeVisOne-VL-2B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-wevisone-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-wevisone-vl-4b.json", "title": "Kimi K3 vs WeVisOne-VL-4B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-wevisone-vl-4b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-zaya1-8b.json", "title": "Kimi K3 vs ZAYA1-8B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-zaya1-8b" } ], "panel": null, "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 10, "edge": "kimi-k3", "inkling-2-small": 40, "key": "reach", "kimi-k3": 50, "name": "Reach", "weight": 25 }, { "by": 0, "edge": "", "inkling-2-small": 65, "key": "risk", "kimi-k3": 65, "name": "Risk", "weight": 20 }, { "by": 20, "edge": "inkling-2-small", "inkling-2-small": 85, "key": "interface", "kimi-k3": 65, "name": "Agent interface", "weight": 10 }, { "by": 26, "edge": "inkling-2-small", "inkling-2-small": 67, "key": "upkeep", "kimi-k3": 41, "name": "Documentation and upkeep", "weight": 10 } ], "summary": "Kimi K3 scores 62.4 (B) on agent readiness against Inkling 2 Small's 58.8 (C), and leads in 1 of 4 scored categories. Inkling 2 Small leads on agent interface and documentation and upkeep. Both do open-weight models you run yourself.", "tasks": null, "tutorials": [], "verdicts": { "inkling-2-small": "Thinking Machines' newest open model, a 594B mixture-of-experts generalist with images in, several tool calls a turn and per-request thinking effort. The NVFP4 checkpoint needs about 472 GB, and no released runtime runs it yet, so today that means vLLM's or SGLang's own images, or Tinker and Together hosted. The use policy binds on download and can change.", "kimi-k3": "Kimi K3 is a 2.8T multimodal agent model with a 1M-token context, parallel tool calls and per-request effort, for long coding and research sessions. Its 1,561 GB of files need a multi-node GPU cluster, so most agents will call a hosted copy. The main risks are Moonshot's Python running at load and prompt time, and no answers in its repository." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3", "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3.min.md" }, "markdown": "Kimi K3 scores 62.4 (B) on agent readiness against Inkling 2 Small's 58.8 (C), and leads in 1 of 4 scored categories. Inkling 2 Small leads on agent interface and documentation and upkeep. Both do open-weight models you run yourself.\n\n- Inkling 2 Small: grade C, 58.8/100, rank #102 of 161 open-weight models. Markdown https://www.anchorterminal.com/tools/inkling-2-small.md · JSON https://www.anchorterminal.com/api/v1/tools/inkling-2-small.json\n- Kimi K3: grade B, 62.4/100, rank #30 of 161 open-weight models. Markdown https://www.anchorterminal.com/tools/kimi-k3.md · JSON https://www.anchorterminal.com/api/v1/tools/kimi-k3.json\n- Best open-weight models you download and run yourself for AI agents: https://www.anchorterminal.com/best/open-weights/index.md\n- All 6472 open weights comparisons: https://www.anchorterminal.com/compare/open-weights/index.md\n\n## Which one, for what\n\n### Inkling 2 Small (C)\n\nGood for: Teams with 512 GB or more of datacentre GPU memory who want Thinking Machines' newest open multimodal agent model and can run a runtime's pre-release image.\n\nAhead on:\n- Agent interface, 85 against 65\n- Documentation and upkeep, 67 against 41\n\nWatch for: The smaller checkpoint needs about 472 GB, and Thinking Machines says 500 GB of GPU memory\n\n### Kimi K3 (B)\n\nGood for: Teams with a multi-node GPU cluster who want an open 1M-context agent model for long coding and research work\n\nAhead on:\n- Reach, 50 against 40\n\nWatch for: 1,561 GB of files at its smallest publisher build, far beyond any single machine\n\n\n## Why the edge\n\n### Documentation and upkeep: Inkling 2 Small +26\n\n- Inkling 2 Small (67): Model card 17 of 20, everything but a dated knowledge cut-off. Training data 15, an EU training-content summary with sources, mix, an October 2026 collection cut-off and filtering. Last change 20, the files were uploaded on 12 November 2026. Responsiveness 0, the repository has no questions yet, which reads as none answered. Version policy 5, a first release. File health 10, the files agree and no broken-file report waits. 17 + 15 + 20 + 0 + 5 + 10 = 67.\n- Kimi K3 (41): The model card earns 11, covering intended use, architecture, parameters and context, but not limitations, languages or a knowledge cut-off. Training data earns 5 for a general description with no cut-off. The last change earns 15, an encoding_k3.py update on 20 August, 74 days before 2 November and within 90; the GitHub repository's last commit is 6 August. Responsiveness earns nothing, with no Moonshot reply in the 40 most recent discussions. Version policy earns 5 for a first release. File health earns 5, because a report that the tokeniser goes past the declared vocabulary waits without a reply.\n\n### Agent interface: Inkling 2 Small +20\n\n- Inkling 2 Small (85): Chat template 20, a Jinja file in the repository. Tool-calling format 25, Thinking Machines' tml-renderers guide shows how tools are declared and how calls come back for this model, and its package ships the parser. Trained tool calling 20, several calls in one turn. Structured output 0, not documented. Reasoning control 10, thinking effort is set per request from none to xhigh, and the reasoning comes back in reasoning_content. Context 10, up to 1M tokens. 20 + 25 + 20 + 0 + 10 + 10 = 85.\n- Kimi K3 (65): The chat template earns 10, because there is no Jinja template and the prompt format exists only as encoding_k3.py, code you run. The tool-calling format earns 10, since Moonshot documents the tools channel but the parser name comes only from vLLM's and SGLang's own recipes. Trained tool calling earns 20 for indexed parallel calls in one turn. Structured output earns 5, as the card names it among its linked guides without saying how to ask the weights for it, and the how sits in hosted-API docs. Reasoning control earns 10, with per-request effort documented on the card and reasoning returned as reasoning_content. Context earns 10 for 1,048,576 tokens trained in.\n\n### Reach: Kimi K3 +10\n\n- Inkling 2 Small (40): Memory 0 of 30, the smallest build is Thinking Machines' NVFP4 checkpoint at 393.5 GB, about 472 GB with a fifth added, above the 256 GB line. Runtimes 0, no released version of the six runs it; vLLM and SGLang serve it from their own images and Transformers has it on its main branch only. Builds 15, two precisions from the publisher (NVFP4 and MXFP8). Terms 10, Apache 2.0 with a binding acceptable use policy on top, read as a custom licence. Download 10, no gate. Hosted 5, Thinking Machines' own Tinker serves it as beta serverless inference, and Together is live on Hugging Face. 0 + 0 + 15 + 10 + 10 + 5 = 40.\n- Kimi K3 (50): Memory earns nothing, because the only build of 4-bit precision or better from Moonshot or a runtime's own library is Moonshot's MXFP4 release of 1,561 GB, about 1,873 GB with the fifth added, far above 256 GB. Ollama and LM Studio list it only as a cloud model. Runtimes earn 15, for model code in released vLLM, SGLang and llama.cpp; Transformers has no kimi_k3 code of its own and loads Moonshot's remote code, so it doesn't count. Builds earn 10 for one publisher precision, the MXFP4 files the model was trained for. Terms earn 10, a custom MIT-based licence that is free for commercial use below a revenue threshold. Download earns 10, with no gate and no account. Hosted earns 5, since Moonshot's API serves it and five inference providers are live for it on Hugging Face.\n\n## Score by category\n\n| Category | Weight | Inkling 2 Small | Kimi K3 | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 40 | 50 | Kimi K3 +10 |\n| Risk | 20% (20 this run) | 65 | 65 | even |\n| Agent interface | 10% (10 this run) | 85 | 65 | Inkling 2 Small +20 |\n| Documentation and upkeep | 10% (10 this run) | 67 | 41 | Inkling 2 Small +26 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **58.8 · C** | **62.4 · B** | |\n\n## Facts side by side\n\n| Fact | Inkling 2 Small | Kimi K3 |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Thinking Machines Lab | Moonshot AI |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | Kimi K3 License (modified MIT) |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-11-12 | 2026-09-02 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Agent reviews | none | 2.3/5 (4) |\n\n## How the scores have moved\n\n### Inkling 2 Small\n\n- +6.7 on 12 November 2026 (D to C): product\n\n### Kimi K3\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Inkling 2 Small.** Thinking Machines' newest open model, a 594B mixture-of-experts generalist with images in, several tool calls a turn and per-request thinking effort. The NVFP4 checkpoint needs about 472 GB, and no released runtime runs it yet, so today that means vLLM's or SGLang's own images, or Tinker and Together hosted. The use policy binds on download and can change.\n\n**Kimi K3.** Kimi K3 is a 2.8T multimodal agent model with a 1M-token context, parallel tool calls and per-request effort, for long coding and research sessions. Its 1,561 GB of files need a multi-node GPU cluster, so most agents will call a hosted copy. The main risks are Moonshot's Python running at load and prompt time, and no answers in its repository.\n\n## Before you call either\n\n### Inkling 2 Small\n\n1. No released runtime runs it yet. Serve the NVFP4 checkpoint from SGLang's dev-inkling-2-small image with the cookbook's recipe for your hardware, or from vLLM's vllm/vllm-openai:inkling-2-small image\n2. In vLLM pass `--reasoning-parser inkling --enable-auto-tool-choice --tool-call-parser inkling`. In SGLang the tool-call parser is `inkling2` and the reasoning parser `inkling`\n3. Transformers' main branch loads only thinkingmachines/Inkling-2-Small-MXFP8, the 622.8 GB checkpoint, and no release has the code yet\n4. Pass `reasoning_effort` as none, minimal, low, medium, high (the default), xhigh or max, or a number from 0 to 0.99\n5. Effort none conditions the model toward no reasoning but doesn't forbid it, and higher effort needs a larger max_tokens\n6. Tool call arguments must reach the template as an object, not a JSON string, or it raises an error\n7. Images should be 40 to 4096 px a side. The model takes no audio, and the template raises an error for an audio part\n8. Use guided decoding or validate JSON yourself, since structured output isn't documented\n9. Without the hardware, call it on Tinker's OpenAI-compatible endpoint with a Tinker key, at $0.30 input and $1.00 output per million tokens as read on 6 November 2026\n10. Read the Model Acceptable Use Policy before deploying, it binds on download and bars some uses that are legal\n\n### Kimi K3\n\n1. Start it with SGLang on a node of 8 B300s, sglang serve --trust-remote-code --model-path moonshotai/Kimi-K3 --tp-size 8 --context-length 65536 --mem-fraction-static 0.82 --reasoning-parser kimi_k3 --tool-call-parser kimi_k3 --port 30000\n2. Use the kimi_k3 tool-call and reasoning parsers in vLLM or SGLang, and validate tool-call arguments against the schema, since vLLM's recipe says K3 sometimes emits a format its parser doesn't expect\n3. Pass the whole assistant message back every turn, reasoning_content and tool_calls included, or output becomes unstable\n4. Thinking is always on; set reasoning_effort to low or high when max is too slow\n5. Sampling per the card is temperature 1.0, with top-p 0.95 for single-step tasks and 1.0 for agentic ones\n6. Don't hand an ongoing session from another model to K3, and state boundaries in the system prompt, since Moonshot warns it can act on its own when intent is unclear\n7. Without the hardware, call it through Moonshot's API or an inference provider listed on its Hugging Face page\n\n## Questions\n\n### Which is better for AI agents, Inkling 2 Small or Kimi K3?\n\nKimi K3 scores 62.4 (B) on agent readiness against Inkling 2 Small's 58.8 (C), and leads in 1 of 4 scored categories. Inkling 2 Small leads on agent interface and documentation and upkeep.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3.json, and with the fewest tokens: https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"inkling-2-small\", \"b\": \"kimi-k3\"}`. From a terminal: `anchor compare inkling-2-small kimi-k3`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/inkling-2-small.json and https://www.anchorterminal.com/api/v1/tools/kimi-k3.json\n\n## Other comparisons with Inkling 2 Small or Kimi K3\n\n- [Agents-A1-4B vs Inkling 2 Small](https://www.anchorterminal.com/compare/agents-a1-4b-vs-inkling-2-small.md)\n- [Agents-A1-4B vs Kimi K3](https://www.anchorterminal.com/compare/agents-a1-4b-vs-kimi-k3.md)\n- [Apertus v1.5 8B vs Inkling 2 Small](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-inkling-2-small.md)\n- [Apertus v1.5 8B vs Kimi K3](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-kimi-k3.md)\n- [Apodex-1.1-mini vs Inkling 2 Small](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-inkling-2-small.md)\n- [Apodex-1.1-mini vs Kimi K3](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-kimi-k3.md)\n- [Arete-27B vs Inkling 2 Small](https://www.anchorterminal.com/compare/arete-27b-vs-inkling-2-small.md)\n- [Arete-27B vs Kimi K3](https://www.anchorterminal.com/compare/arete-27b-vs-kimi-k3.md)\n- [BigBang-v1 vs Inkling 2 Small](https://www.anchorterminal.com/compare/bigbang-v1-vs-inkling-2-small.md)\n- [BigBang-v1 vs Kimi K3](https://www.anchorterminal.com/compare/bigbang-v1-vs-kimi-k3.md)\n- [Carbon-X vs Inkling 2 Small](https://www.anchorterminal.com/compare/carbon-x-vs-inkling-2-small.md)\n- [Carbon-X vs Kimi K3](https://www.anchorterminal.com/compare/carbon-x-vs-kimi-k3.md)\n- [Cola2 vs Inkling 2 Small](https://www.anchorterminal.com/compare/cola2-vs-inkling-2-small.md)\n- [Cola2 vs Kimi K3](https://www.anchorterminal.com/compare/cola2-vs-kimi-k3.md)\n- [Cosmos-Reason2-2B vs Inkling 2 Small](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-inkling-2-small.md)\n- [Cosmos-Reason2-2B vs Kimi K3](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-kimi-k3.md)\n- [Darwin-36B-Opus vs Inkling 2 Small](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-inkling-2-small.md)\n- [Darwin-36B-Opus vs Kimi K3](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-kimi-k3.md)\n- [DeepSeek-V3.2 vs Inkling 2 Small](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling-2-small.md)\n- [DeepSeek-V3.2 vs Kimi K3](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-kimi-k3.md)\n- [DeepSeek V4.1 Flash vs Inkling 2 Small](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-inkling-2-small.md)\n- [DeepSeek V4.1 Flash vs Kimi K3](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-kimi-k3.md)\n- [DeepSeek-V4-Flash-0731 vs Inkling 2 Small](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-inkling-2-small.md)\n- [DeepSeek-V4-Flash-0731 vs Kimi K3](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-kimi-k3.md)\n- [Devstral Small 2 vs Inkling 2 Small](https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling-2-small.md)\n- [Devstral Small 2 vs Kimi K3](https://www.anchorterminal.com/compare/devstral-small-2-vs-kimi-k3.md)\n- [DiffusionGemma 26B A4B IT vs Inkling 2 Small](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling-2-small.md)\n- [DiffusionGemma 26B A4B IT vs Kimi K3](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-kimi-k3.md)\n- [EXAONE 4.5 33B vs Inkling 2 Small](https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-inkling-2-small.md)\n- [EXAONE 4.5 33B vs Kimi K3](https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-kimi-k3.md)\n- [Gemma 4 12B IT vs Inkling 2 Small](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-inkling-2-small.md)\n- [Gemma 4 12B IT vs Kimi K3](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-kimi-k3.md)\n- [Gemma 4 26B A4B IT vs Inkling 2 Small](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-inkling-2-small.md)\n- [Gemma 4 26B A4B IT vs Kimi K3](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-kimi-k3.md)\n- [Gemma 4 31B IT vs Inkling 2 Small](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-inkling-2-small.md)\n- [Gemma 4 31B IT vs Kimi K3](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-kimi-k3.md)\n- [Gemma 4 E2B IT vs Inkling 2 Small](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-inkling-2-small.md)\n- [Gemma 4 E2B IT vs Kimi K3](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-kimi-k3.md)\n- [Gemma 4 E4B IT vs Inkling 2 Small](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-inkling-2-small.md)\n- [Gemma 4 E4B IT vs Kimi K3](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-kimi-k3.md)\n- [GLM-4.5-Air vs Inkling 2 Small](https://www.anchorterminal.com/compare/glm-4-5-air-vs-inkling-2-small.md)\n- [GLM-4.5-Air vs Kimi K3](https://www.anchorterminal.com/compare/glm-4-5-air-vs-kimi-k3.md)\n- [GLM-4.7-Flash vs Inkling 2 Small](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-inkling-2-small.md)\n- [GLM-4.7-Flash vs Kimi K3](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-kimi-k3.md)\n- [GLM-5.3-Flash vs Inkling 2 Small](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling-2-small.md)\n- [GLM-5.3-Flash vs Kimi K3](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-kimi-k3.md)\n- [GLM-5.3 vs Inkling 2 Small](https://www.anchorterminal.com/compare/glm-5-3-vs-inkling-2-small.md)\n- [GLM-5.3 vs Kimi K3](https://www.anchorterminal.com/compare/glm-5-3-vs-kimi-k3.md)\n- [gpt-oss-120b vs Inkling 2 Small](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-inkling-2-small.md)\n- [gpt-oss-120b vs Kimi K3](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-kimi-k3.md)\n- [gpt-oss-20b vs Inkling 2 Small](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling-2-small.md)\n- [gpt-oss-20b vs Kimi K3](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-kimi-k3.md)\n- [Granite 4.2 30B vs Inkling 2 Small](https://www.anchorterminal.com/compare/granite-4-2-30b-vs-inkling-2-small.md)\n- [Granite 4.2 30B vs Kimi K3](https://www.anchorterminal.com/compare/granite-4-2-30b-vs-kimi-k3.md)\n- [Granite 4.2 3B vs Inkling 2 Small](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-inkling-2-small.md)\n- [Granite 4.2 3B vs Kimi K3](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-kimi-k3.md)\n- [Granite 4.2 8B vs Inkling 2 Small](https://www.anchorterminal.com/compare/granite-4-2-8b-vs-inkling-2-small.md)\n- [Granite 4.2 8B vs Kimi K3](https://www.anchorterminal.com/compare/granite-4-2-8b-vs-kimi-k3.md)\n- [Hy-Memory-30B-A3B vs Inkling 2 Small](https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-inkling-2-small.md)\n- [Hy-Memory-30B-A3B vs Kimi K3](https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-kimi-k3.md)\n- [Hy3 vs Inkling 2 Small](https://www.anchorterminal.com/compare/hy3-vs-inkling-2-small.md)\n- [Hy3 vs Kimi K3](https://www.anchorterminal.com/compare/hy3-vs-kimi-k3.md)\n- [Inkling 2 Small vs Inkling-Small](https://www.anchorterminal.com/compare/inkling-2-small-vs-inkling-small.md)\n- [Inkling 2 Small vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/inkling-2-small-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)\n- [Inkling 2 Small vs Kimi K3.1 Pro](https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3-1-pro.md)\n- [Inkling 2 Small vs Kolibri-1](https://www.anchorterminal.com/compare/inkling-2-small-vs-kolibri-1.md)\n- [Inkling 2 Small vs Kronos](https://www.anchorterminal.com/compare/inkling-2-small-vs-kronos.md)\n- [Inkling 2 Small vs Laguna M.1](https://www.anchorterminal.com/compare/inkling-2-small-vs-laguna-m-1.md)\n- [Inkling 2 Small vs Laguna S 2.1](https://www.anchorterminal.com/compare/inkling-2-small-vs-laguna-s-2-1.md)\n- [Inkling 2 Small vs Laguna XS 2.1](https://www.anchorterminal.com/compare/inkling-2-small-vs-laguna-xs-2-1.md)\n- [Inkling 2 Small vs LBS-27B](https://www.anchorterminal.com/compare/inkling-2-small-vs-lbs-27b.md)\n- [Inkling 2 Small vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm2-5-2-6b.md)\n- [Inkling 2 Small vs LFM3-1.7B](https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-1-7b.md)\n- [Inkling 2 Small vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-audio-2b.md)\n- [Inkling 2 Small vs LFM3-Omni-2B](https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-omni-2b.md)\n- [Inkling 2 Small vs LFM3-VL-2B](https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-vl-2b.md)\n- [Inkling 2 Small vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/inkling-2-small-vs-ling-3-0-tiny.md)\n- [Inkling 2 Small vs Ling-3.1-flash-1019](https://www.anchorterminal.com/compare/inkling-2-small-vs-ling-3-1-flash-1019.md)\n- [Inkling 2 Small vs LongCat-2.5](https://www.anchorterminal.com/compare/inkling-2-small-vs-longcat-2-5.md)\n- [Inkling 2 Small vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/inkling-2-small-vs-mimo-v2-6-distill-qwen-9b.md)\n- [Inkling 2 Small vs MiMo-V2.6-Flash-RL](https://www.anchorterminal.com/compare/inkling-2-small-vs-mimo-v2-6-flash-rl.md)\n- [Inkling 2 Small vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm-o-4-5.md)\n- [Inkling 2 Small vs MiniCPM-V 4.7 1B](https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm-v-4-7-1b.md)\n- [Inkling 2 Small vs MiniCPM-V 4.7 35B-A3B](https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm-v-4-7-35b-a3b.md)\n- [Inkling 2 Small vs MiniCPM5-2B](https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm5-2b.md)\n- [Inkling 2 Small vs MiniMax-M2.5](https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m2-5.md)\n- [Inkling 2 Small vs MiniMax-M2.7](https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m2-7.md)\n- [Inkling 2 Small vs MiniMax-M3.1-Flash](https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m3-1-flash.md)\n- [Inkling 2 Small vs Mistral Large 4](https://www.anchorterminal.com/compare/inkling-2-small-vs-mistral-large-4.md)\n- [Inkling 2 Small vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-glimmer-30b.md)\n- [Inkling 2 Small vs Nanbeige4.2-3B](https://www.anchorterminal.com/compare/inkling-2-small-vs-nanbeige-4-2-3b.md)\n- [Inkling 2 Small vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/inkling-2-small-vs-nanbeige-4-3-33b.md)\n- [Inkling 2 Small vs NVIDIA Nemotron 3.5 Bolt E4B 4GB](https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-bolt-e4b-4gb.md)\n- [Inkling 2 Small vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [Inkling 2 Small vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-nano-30b-a3b.md)\n- [Inkling 2 Small vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-nano-4b.md)\n- [Inkling 2 Small vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [Inkling 2 Small vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-super-120b-a12b.md)\n- [Inkling 2 Small vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-ultra-550b-a55b.md)\n- [Inkling 2 Small vs North Mini Code 1.0](https://www.anchorterminal.com/compare/inkling-2-small-vs-north-mini-code-1-0.md)\n- [Inkling 2 Small vs occamy-1.0](https://www.anchorterminal.com/compare/inkling-2-small-vs-occamy-1-0.md)\n- [Inkling 2 Small vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/inkling-2-small-vs-olmo-3-7b-think.md)\n- [Inkling 2 Small vs Ornith-1.5-122B](https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-122b.md)\n- [Inkling 2 Small vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-35b-a3b.md)\n- [Inkling 2 Small vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-397b.md)\n- [Inkling 2 Small vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-9b.md)\n- [Inkling 2 Small vs OTel-2.0-LLM-31B-IT](https://www.anchorterminal.com/compare/inkling-2-small-vs-otel-2-0-llm-31b-it.md)\n- [Inkling 2 Small vs Qwen-AgentWorld-35B-A3B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen-agentworld-35b-a3b.md)\n- [Inkling 2 Small vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-30b-a3b-instruct-2507.md)\n- [Inkling 2 Small vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-4b-instruct-2507.md)\n- [Inkling 2 Small vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-0-8b.md)\n- [Inkling 2 Small vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-122b-a10b.md)\n- [Inkling 2 Small vs Qwen3.5-2B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-2b.md)\n- [Inkling 2 Small vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-397b-a17b.md)\n- [Inkling 2 Small vs Qwen3.5-4B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-4b.md)\n- [Inkling 2 Small vs Qwen3.5-9B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-9b.md)\n- [Inkling 2 Small vs Qwen3.6-27B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-6-27b.md)\n- [Inkling 2 Small vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-6-35b-a3b.md)\n- [Inkling 2 Small vs Qwen3.8-27B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-8-27b.md)\n- [Inkling 2 Small vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-8-flash-next.md)\n- [Inkling 2 Small vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-coder-30b-a3b-instruct.md)\n- [Inkling 2 Small vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-coder-next.md)\n- [Inkling 2 Small vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Inkling 2 Small vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-2b-instruct.md)\n- [Inkling 2 Small vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-30b-a3b-instruct.md)\n- [Inkling 2 Small vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-32b-instruct.md)\n- [Inkling 2 Small vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-4b-instruct.md)\n- [Inkling 2 Small vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-8b-instruct.md)\n- [Inkling 2 Small vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwopus3-8-27b-flash-v2.md)\n- [Inkling 2 Small vs Recursive Flint](https://www.anchorterminal.com/compare/inkling-2-small-vs-recursive-flint.md)\n- [Inkling 2 Small vs Ripple-65B Preview](https://www.anchorterminal.com/compare/inkling-2-small-vs-ripple-65b-preview.md)\n- [Inkling 2 Small vs SenseNova-Loop-9B-Preview](https://www.anchorterminal.com/compare/inkling-2-small-vs-sensenova-loop-9b-preview.md)\n- [Inkling 2 Small vs SmolLM3-3B](https://www.anchorterminal.com/compare/inkling-2-small-vs-smollm3-3b.md)\n- [Inkling 2 Small vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/inkling-2-small-vs-spark-x2-6-4b.md)\n- [Inkling 2 Small vs Step 3.7 Flash](https://www.anchorterminal.com/compare/inkling-2-small-vs-step-3-7-flash.md)\n- [Inkling 2 Small vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/inkling-2-small-vs-swift-1-5-qwen3-8-27b.md)\n- [Inkling 2 Small vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/inkling-2-small-vs-swift-1-5-qwen3-8-flash-next.md)\n- [Inkling 2 Small vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/inkling-2-small-vs-thinkingcap-qwen3-8-27b.md)\n- [Inkling 2 Small vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/inkling-2-small-vs-unlimited-ocr-2.md)\n- [Inkling 2 Small vs WeVisOne-VL-2B](https://www.anchorterminal.com/compare/inkling-2-small-vs-wevisone-vl-2b.md)\n- [Inkling 2 Small vs WeVisOne-VL-4B](https://www.anchorterminal.com/compare/inkling-2-small-vs-wevisone-vl-4b.md)\n- [Inkling 2 Small vs ZAYA1-8B](https://www.anchorterminal.com/compare/inkling-2-small-vs-zaya1-8b.md)\n- [Inkling-Small vs Kimi K3](https://www.anchorterminal.com/compare/inkling-small-vs-kimi-k3.md)\n- [Inkling vs Inkling 2 Small](https://www.anchorterminal.com/compare/inkling-vs-inkling-2-small.md)\n- [Inkling vs Kimi K3](https://www.anchorterminal.com/compare/inkling-vs-kimi-k3.md)\n- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Kimi K3](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-kimi-k3.md)\n- [Kimi K3 vs Kimi K3.1 Pro](https://www.anchorterminal.com/compare/kimi-k3-vs-kimi-k3-1-pro.md)\n- [Kimi K3 vs Kolibri-1](https://www.anchorterminal.com/compare/kimi-k3-vs-kolibri-1.md)\n- [Kimi K3 vs Kronos](https://www.anchorterminal.com/compare/kimi-k3-vs-kronos.md)\n- [Kimi K3 vs Laguna M.1](https://www.anchorterminal.com/compare/kimi-k3-vs-laguna-m-1.md)\n- [Kimi K3 vs Laguna S 2.1](https://www.anchorterminal.com/compare/kimi-k3-vs-laguna-s-2-1.md)\n- [Kimi K3 vs Laguna XS 2.1](https://www.anchorterminal.com/compare/kimi-k3-vs-laguna-xs-2-1.md)\n- [Kimi K3 vs LBS-27B](https://www.anchorterminal.com/compare/kimi-k3-vs-lbs-27b.md)\n- [Kimi K3 vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/kimi-k3-vs-lfm2-5-2-6b.md)\n- [Kimi K3 vs LFM3-1.7B](https://www.anchorterminal.com/compare/kimi-k3-vs-lfm3-1-7b.md)\n- [Kimi K3 vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/kimi-k3-vs-lfm3-audio-2b.md)\n- [Kimi K3 vs LFM3-Omni-2B](https://www.anchorterminal.com/compare/kimi-k3-vs-lfm3-omni-2b.md)\n- [Kimi K3 vs LFM3-VL-2B](https://www.anchorterminal.com/compare/kimi-k3-vs-lfm3-vl-2b.md)\n- [Kimi K3 vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/kimi-k3-vs-ling-3-0-tiny.md)\n- [Kimi K3 vs Ling-3.1-flash-1019](https://www.anchorterminal.com/compare/kimi-k3-vs-ling-3-1-flash-1019.md)\n- [Kimi K3 vs LongCat-2.5](https://www.anchorterminal.com/compare/kimi-k3-vs-longcat-2-5.md)\n- [Kimi K3 vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/kimi-k3-vs-mimo-v2-6-distill-qwen-9b.md)\n- [Kimi K3 vs MiMo-V2.6-Flash-RL](https://www.anchorterminal.com/compare/kimi-k3-vs-mimo-v2-6-flash-rl.md)\n- [Kimi K3 vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/kimi-k3-vs-minicpm-o-4-5.md)\n- [Kimi K3 vs MiniCPM-V 4.7 1B](https://www.anchorterminal.com/compare/kimi-k3-vs-minicpm-v-4-7-1b.md)\n- [Kimi K3 vs MiniCPM-V 4.7 35B-A3B](https://www.anchorterminal.com/compare/kimi-k3-vs-minicpm-v-4-7-35b-a3b.md)\n- [Kimi K3 vs MiniCPM5-2B](https://www.anchorterminal.com/compare/kimi-k3-vs-minicpm5-2b.md)\n- [Kimi K3 vs MiniMax-M2.5](https://www.anchorterminal.com/compare/kimi-k3-vs-minimax-m2-5.md)\n- [Kimi K3 vs MiniMax-M2.7](https://www.anchorterminal.com/compare/kimi-k3-vs-minimax-m2-7.md)\n- [Kimi K3 vs MiniMax-M3.1-Flash](https://www.anchorterminal.com/compare/kimi-k3-vs-minimax-m3-1-flash.md)\n- [Kimi K3 vs Mistral Large 4](https://www.anchorterminal.com/compare/kimi-k3-vs-mistral-large-4.md)\n- [Kimi K3 vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/kimi-k3-vs-muse-glimmer-30b.md)\n- [Kimi K3 vs Nanbeige4.2-3B](https://www.anchorterminal.com/compare/kimi-k3-vs-nanbeige-4-2-3b.md)\n- [Kimi K3 vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/kimi-k3-vs-nanbeige-4-3-33b.md)\n- [Kimi K3 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB](https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-5-bolt-e4b-4gb.md)\n- [Kimi K3 vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [Kimi K3 vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-nano-30b-a3b.md)\n- [Kimi K3 vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-nano-4b.md)\n- [Kimi K3 vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [Kimi K3 vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-super-120b-a12b.md)\n- [Kimi K3 vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/kimi-k3-vs-nemotron-3-ultra-550b-a55b.md)\n- [Kimi K3 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/kimi-k3-vs-north-mini-code-1-0.md)\n- [Kimi K3 vs occamy-1.0](https://www.anchorterminal.com/compare/kimi-k3-vs-occamy-1-0.md)\n- [Kimi K3 vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/kimi-k3-vs-olmo-3-7b-think.md)\n- [Kimi K3 vs Ornith-1.5-122B](https://www.anchorterminal.com/compare/kimi-k3-vs-ornith-1-5-122b.md)\n- [Kimi K3 vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/kimi-k3-vs-ornith-1-5-35b-a3b.md)\n- [Kimi K3 vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/kimi-k3-vs-ornith-1-5-397b.md)\n- [Kimi K3 vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/kimi-k3-vs-ornith-1-5-9b.md)\n- [Kimi K3 vs OTel-2.0-LLM-31B-IT](https://www.anchorterminal.com/compare/kimi-k3-vs-otel-2-0-llm-31b-it.md)\n- [Kimi K3 vs Qwen-AgentWorld-35B-A3B](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen-agentworld-35b-a3b.md)\n- [Kimi K3 vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-30b-a3b-instruct-2507.md)\n- [Kimi K3 vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-4b-instruct-2507.md)\n- [Kimi K3 vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-5-0-8b.md)\n- [Kimi K3 vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-5-122b-a10b.md)\n- [Kimi K3 vs Qwen3.5-2B](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-5-2b.md)\n- [Kimi K3 vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-5-397b-a17b.md)\n- [Kimi K3 vs Qwen3.5-4B](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-5-4b.md)\n- [Kimi K3 vs Qwen3.5-9B](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-5-9b.md)\n- [Kimi K3 vs Qwen3.6-27B](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-6-27b.md)\n- [Kimi K3 vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-6-35b-a3b.md)\n- [Kimi K3 vs Qwen3.8-27B](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-8-27b.md)\n- [Kimi K3 vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-8-flash-next.md)\n- [Kimi K3 vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-coder-30b-a3b-instruct.md)\n- [Kimi K3 vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-coder-next.md)\n- [Kimi K3 vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Kimi K3 vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-vl-2b-instruct.md)\n- [Kimi K3 vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-vl-30b-a3b-instruct.md)\n- [Kimi K3 vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-vl-32b-instruct.md)\n- [Kimi K3 vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-vl-4b-instruct.md)\n- [Kimi K3 vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/kimi-k3-vs-qwen3-vl-8b-instruct.md)\n- [Kimi K3 vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/kimi-k3-vs-qwopus3-8-27b-flash-v2.md)\n- [Kimi K3 vs Recursive Flint](https://www.anchorterminal.com/compare/kimi-k3-vs-recursive-flint.md)\n- [Kimi K3 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/kimi-k3-vs-ripple-65b-preview.md)\n- [Kimi K3 vs SenseNova-Loop-9B-Preview](https://www.anchorterminal.com/compare/kimi-k3-vs-sensenova-loop-9b-preview.md)\n- [Kimi K3 vs SmolLM3-3B](https://www.anchorterminal.com/compare/kimi-k3-vs-smollm3-3b.md)\n- [Kimi K3 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/kimi-k3-vs-spark-x2-6-4b.md)\n- [Kimi K3 vs Step 3.7 Flash](https://www.anchorterminal.com/compare/kimi-k3-vs-step-3-7-flash.md)\n- [Kimi K3 vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/kimi-k3-vs-swift-1-5-qwen3-8-27b.md)\n- [Kimi K3 vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/kimi-k3-vs-swift-1-5-qwen3-8-flash-next.md)\n- [Kimi K3 vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/kimi-k3-vs-thinkingcap-qwen3-8-27b.md)\n- [Kimi K3 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/kimi-k3-vs-unlimited-ocr-2.md)\n- [Kimi K3 vs WeVisOne-VL-2B](https://www.anchorterminal.com/compare/kimi-k3-vs-wevisone-vl-2b.md)\n- [Kimi K3 vs WeVisOne-VL-4B](https://www.anchorterminal.com/compare/kimi-k3-vs-wevisone-vl-4b.md)\n- [Kimi K3 vs ZAYA1-8B](https://www.anchorterminal.com/compare/kimi-k3-vs-zaya1-8b.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-15", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.8", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Inkling 2 Small vs Kimi K3", "url": "" } ], "description": "Kimi K3 scores 62.4 (B) to Inkling 2 Small's 58.8 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Inkling 2 Small C 58.8", "Kimi K3 B 62.4", "scores" ], "h1": "Inkling 2 Small vs Kimi K3", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/inkling-2-small-vs-kimi-k3", "published": "2026-10-01", "section": "tools", "title": "Inkling 2 Small vs Kimi K3 for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-12", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3" }, "tokens": { "markdown": 9100, "slim": 680 }, "version": 1 }