{ "data": { "a": { "slug": "inkling", "name": "Inkling", "vendor": "Thinking Machines Lab", "vendorUrl": "https://thinkingmachines.ai", "kind": "weights", "category": "open-weights", "summary": "Inkling is Thinking Machines Lab's large open-weight mixture-of-experts model, 975B total and 41B active parameters, taking text, images and audio and returning text, with adjustable thinking effort, published in BF16 and NVFP4 under Apache 2.0.", "url": "https://www.anchorterminal.com/tools/inkling", "markdownUrl": "https://www.anchorterminal.com/tools/inkling.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/inkling.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/inkling.json", "dns": "inkling.grade.anchorterminal.com", "repo": "https://huggingface.co/thinkingmachines/Inkling", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "thinkingmachines/Inkling" }, { "registry": "huggingface", "name": "thinkingmachines/Inkling-NVFP4" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. Neither repository is gated (checked 2026-10-21). 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, 1,904.8 GB for the BF16 files and 592.0 GB for the NVFP4 build. Thinking Machines' Tinker serves it as a beta serverless inference API at $1.00 per million input tokens and $4.05 per million output tokens (checked 2026-10-21).", "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 2026-10-21).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-02" }, "docsUrl": "https://thinkingmachines.ai/model-card/inkling/", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "moe", "multimodal", "audio", "reasoning", "tool-calling", "apache-2.0", "safetensors", "nvfp4", "self-hosted" ], "lastRelease": "2026-07-23", "graded": true, "anchor": { "graded": true, "score": 64.7, "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": 1518, "categoryRank": 14, "methodology": "0.7", "run": "2026-10-01", "scores": { "capability": 60, "interface": 85, "reach": 50, "risk": 70, "upkeep": 87 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-11-02" }, "negative": 0, "verdict": "Thinking Machines' large multimodal generalist, stronger than Inkling-Small on factual recall by its own numbers. It needs about 710 GB of datacentre GPU memory even in NVFP4, so most agents will use a host such as Together AI or Tinker. The main risks are a use policy that binds on download and can change, and no outside safety results.", "bestFor": "Agents calling a hosted open multimodal model with audio input, or teams with a multi-GPU datacentre node who want to run it themselves.", "strengths": [ "Three inference providers and Thinking Machines' own Tinker host it today", "Safetensors only, with a checksum on every LFS file in the publisher's own organisation", "Thinking effort set per request, several tool calls a turn and a 1M-token context", "Released support in Transformers, vLLM and SGLang, with inkling tool and reasoning parsers", "Thinking Machines answered 8 of the 12 questions and reports in its discussions", "A training-content summary with sources, mix and a July 2026 collection cut-off" ], "weaknesses": [ "The smallest build Thinking Machines publishes needs about 710 GB, beyond any single workstation", "Apache 2.0 comes with an acceptable use policy that binds on download and can change at any time", "No release of ggml-org's llama.cpp, Ollama or LM Studio runs it", "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" ], "agentNotes": [ "Unless you have a multi-GPU Blackwell or H200 node, call it through Together AI, Fireworks, DeepInfra or Tinker rather than starting it", "On 8 B200 GPUs, SGLang's recipe is `sglang serve --trust-remote-code --model-path thinkingmachines/Inkling-NVFP4 --tp 8 --quantization modelopt_fp4 --enable-multimodal --reasoning-parser inkling --tool-call-parser inkling`", "Use the inkling tool parser, not Hermes, and the inkling reasoning parser", "Pass `reasoning_effort` as none, minimal, low, medium, high (the default) or max, or a number from 0 to 0.99. The repository's template has no xhigh preset and raises an error for it, though Thinking Machines' docs list xhigh", "Tool call arguments must reach the template as an object, not a JSON string, or it raises an error", "Audio should be 16 kHz WAV, ideally under 20 minutes, and images 40 to 4096 px a side, per the card", "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": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 64.7 } ], "editorialScores": { "capability": 60, "interface": 85, "reach": 50, "risk": 70, "upkeep": 87 }, "provenanceScore": 71, "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", "lastMoved": "2026-11-02", "oldest": "2026-11-02", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "# per SGLang's cookbook, NVFP4 on 8 B200 GPUs:\nsglang serve --trust-remote-code --model-path thinkingmachines/Inkling-NVFP4 --tp 8 \\\n --quantization modelopt_fp4 --enable-multimodal --reasoning-parser inkling --tool-call-parser inkling", "http": "curl http://localhost:30000/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"model\": \"thinkingmachines/Inkling-NVFP4\",\n \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}],\n \"reasoning_effort\": \"low\"\n }'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/inkling" }, "sameCompany": [ "inkling-2-small", "inkling-small" ], "sameModel": [ "tinker" ], "weights": { "trainedBy": "Thinking Machines Lab", "params": "975B", "active": "41B", "context": 1048576, "goodFor": "Large mixture-of-experts generalist for coding, agents, factual recall and audio, with images in and thinking effort set per request.", "runtimes": [ "vLLM", "SGLang", "Transformers" ], "builds": [ { "name": "Inkling-NVFP4", "url": "https://huggingface.co/thinkingmachines/Inkling-NVFP4", "who": "publisher", "precision": "nvfp4", "sizeGB": 592, "memoryGB": 1024, "format": "safetensors", "note": "NVFP4 experts with FP8 and BF16 parts. Thinking Machines says W4A4 needs NVIDIA SM100 or newer, and W4A16 runs on H200" }, { "name": "Inkling", "url": "https://huggingface.co/thinkingmachines/Inkling", "who": "publisher", "precision": "bf16", "sizeGB": 1904.8, "memoryGB": 4096, "format": "safetensors", "note": "1,904.8 GB × 1.2 = 2,285.7 GB, so the 4,096 GB band. Thinking Machines states at least 2 TB of GPU memory" } ], "run": "sglang serve --trust-remote-code --model-path thinkingmachines/Inkling-NVFP4 --tp 8 --quantization modelopt_fp4 --enable-multimodal --reasoning-parser inkling --tool-call-parser inkling", "runBuild": "Inkling-NVFP4", "checked": "2026-10-21", "minMemoryGB": 1024 }, "family": { "lab": "Thinking Machines Lab", "family": "Inkling", "url": "https://www.anchorterminal.com/open-weights/#thinking-machines", "others": [ { "name": "Inkling-Small", "url": "https://huggingface.co/thinkingmachines/Inkling-Small", "params": "265.96B (Hub safetensors count; the name states none)", "listing": "https://www.anchorterminal.com/tools/inkling-small" } ], "unrestrictedCopies": 1 }, "area": "models", "provenance": { "legalEntity": "Thinking Machines Lab, Inc. (named on its model card page and in its training-content summary)", "domain": "thinkingmachines.ai", "domainRegistered": "", "domainNote": "thinkingmachines.ai's registration date wasn't read on 21 October 2026.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/thinkingmachines/Inkling/commits/main", "securityTxt": "valid", "checked": "2026-10-21", "notes": [ "Thinking Machines' Inkling page links the thinkingmachines collection on Hugging Face, and its model card page links the repository. Hugging Face hasn't verified the organisation.", "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, 13 commits from 15 to 23 July 2026, the upload, a Transformers processor and template change on 15 July, card updates and community evaluation results.", "thinkingmachines.ai/.well-known/security.txt gives a security contact, a PGP key and an expiry in 2029, and the site publishes a coordinated vulnerability disclosure policy that leaves model safety to a separate incident contact." ], "score": 71 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/inkling.json", "live": { "slug": "inkling", "securityTxt": { "url": "https://thinkingmachines.ai/.well-known/security.txt", "state": "valid", "expires": "2029-07-13T07:00:00.000Z", "checkedAt": "2026-11-10T16:08:06.712462129Z" }, "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/commits/main", "kind": "changelog", "status": 200, "checkedAt": "2026-11-10T16:23:50.70345348Z", "changedAt": "2026-11-10T16:23:50.70345348Z", "fingerprint": "60baeb3c18bc" } ], "updatedAt": "2026-11-10T16:23:50.70345348Z" } }, "answer": "Inkling scores 64.7 (B) on agent readiness against LFM3-Audio-2B's 61 (C), and leads in 2 of 4 scored categories. LFM3-Audio-2B leads on reach.", "b": { "slug": "lfm3-audio-2b", "name": "LFM3-Audio-2B", "vendor": "Liquid AI", "vendorUrl": "https://www.liquid.ai", "kind": "weights", "category": "open-weights", "summary": "LFM3-Audio-2B is Liquid AI's open-weight 2B audio model for on-device use, taking text or speech and answering in text, speech or both, with transcription, translation, tool calling and a 32K-token context, released on 27 October 2026.", "url": "https://www.anchorterminal.com/tools/lfm3-audio-2b", "markdownUrl": "https://www.anchorterminal.com/tools/lfm3-audio-2b.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/lfm3-audio-2b.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/lfm3-audio-2b.json", "dns": "lfm3-audio-2b.grade.anchorterminal.com", "repo": "https://huggingface.co/LiquidAI/LFM3-Audio-2B", "license": "LFM Open License v1.0 (free commercial use below $10M annual revenue)", "transports": [], "packages": [ { "registry": "huggingface", "name": "LiquidAI/LFM3-Audio-2B" }, { "registry": "huggingface", "name": "LiquidAI/LFM3-Audio-2B-GGUF" }, { "registry": "huggingface", "name": "LiquidAI/LFM3-Audio-2B-MLX-4bit" }, { "registry": "ollama", "name": "lfm3-audio" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository and Liquid's GGUF, MLX and ONNX repositories are not gated (checked 2026-11-10).", "pricing": "free", "pricingNotes": "Free to download and use under the LFM Open License v1.0, commercial use included for organisations with under $10M in annual revenue; above that, commercial use isn't licensed. Running it yourself costs little hardware, 1.10 GB for Liquid's Q4_K_M GGUF with its 0.17 GB projector file and 4.16 GB in BF16. Liquid's API also serves it, at prices shown in its console (checked 2026-11-10).", "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 2026-11-10).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-10" }, "docsUrl": "https://docs.liquid.ai/lfm/models/lfm3-audio-2b", "llmsTxt": "https://docs.liquid.ai/llms.txt", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "audio", "speech", "speech-to-speech", "transcription", "small", "edge", "tool-calling", "custom-licence", "safetensors", "gguf", "mlx", "onnx", "self-hosted" ], "lastRelease": "2026-11-03", "graded": true, "anchor": { "graded": true, "score": 61, "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": 1518, "categoryRank": 56, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 85, "reach": 80, "risk": 40, "upkeep": 52 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-10" }, "negative": 0, "verdict": "A 2B model that listens and speaks on an 8 GB machine, transcribes and translates 19 languages and turns spoken requests into tool calls. Only llama.cpp and Ollama run it in a release. The context is 32K, voice chat is English only, Liquid hasn't answered the repository's questions, and there are no safety results or data sources.", "bestFor": "Voice agents on a laptop or phone that need speech in, speech out and tool calls from one small model", "strengths": [ "Speech in and speech out on an 8 GB machine, streamed", "Transcribes, speaks and translates 19 languages and locales", "Tool calls from spoken requests, in a documented format", "Reasoning can be turned on per text reply", "Liquid's own API serves it" ], "weaknesses": [ "Only llama.cpp and Ollama run it in a release, though the card lists vLLM and SGLang", "A 32K-token context", "Voice chat is English only", "Neither question on the repository has a reply from Liquid", "Loading in Transformers runs code from the repository", "No safety results, security contact or training data description" ], "agentNotes": [ "Start it with `llama-server -hf LiquidAI/LFM3-Audio-2B-GGUF:Q4_K_M --jinja` or `ollama run lfm3-audio`", "llama.cpp ships examples/realtime_client.py for live speech with this model", "Prefill the assistant turn with an open think tag to let it reason before a text reply", "The context is 32K", "Voice chat is English only, while transcription, synthesis and translation cover 19 languages and locales", "Liquid doesn't recommend it for agentic coding or complex multi-step reasoning" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61 } ], "editorialScores": { "interface": 85, "reach": 80, "risk": 40, "upkeep": 52 }, "provenanceScore": 73, "checked": { "categories": { "interface": "2026-11-10", "reach": "2026-11-10", "risk": "2026-11-10", "upkeep": "2026-11-10" }, "last": "2026-11-10", "oldest": "2026-11-10", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "llama-server -hf LiquidAI/LFM3-Audio-2B-GGUF:Q4_K_M --jinja\n# or\nollama run lfm3-audio", "http": "curl http://localhost:8080/v1/chat/completions \\\n -H 'Content-Type: application/json' \\\n -d '{\"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}]}'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/lfm3-audio-2b" }, "sameCompany": [ "liquid-d1", "lfm2-5-2-6b", "lfm3-1-7b", "lfm3-omni-2b", "lfm3-vl-2b" ], "weights": { "trainedBy": "Liquid AI", "builtOn": "The LFM3 backbone (Liquid's own; the metadata names no base model)", "params": "2.00B", "context": 32000, "goodFor": "Small on-device audio model for voice chat, transcription, speech synthesis and translation in 19 languages and locales, questions about recordings and tool calls from spoken requests. Voice chat is English only.", "runtimes": [ "llama.cpp", "Ollama" ], "builds": [ { "name": "LFM3-Audio-2B", "url": "https://huggingface.co/LiquidAI/LFM3-Audio-2B", "who": "publisher", "precision": "bf16", "sizeGB": 4.16, "memoryGB": 8, "format": "safetensors", "runsOn": [ "Transformers" ], "note": "Loads in Transformers with the repository's own code. Liquid also publishes an ONNX repository. It has no FP8 or NVFP4 build of this model" }, { "name": "LFM3-Audio-2B-GGUF Q8_0", "url": "https://huggingface.co/LiquidAI/LFM3-Audio-2B-GGUF", "who": "publisher", "precision": "q8_0", "sizeGB": 2.15, "memoryGB": 8, "format": "gguf", "runsOn": [ "llama.cpp" ], "note": "LFM3-Audio-2B-Q8_0.gguf (1.85 GB) plus mmproj-LFM3-Audio-2B-Q8_0.gguf (0.30 GB)" }, { "name": "LFM3-Audio-2B-GGUF Q4_K_M", "url": "https://huggingface.co/LiquidAI/LFM3-Audio-2B-GGUF", "who": "publisher", "precision": "q4_k_m", "sizeGB": 1.27, "memoryGB": 8, "format": "gguf", "runsOn": [ "llama.cpp" ], "note": "LFM3-Audio-2B-Q4_K_M.gguf (1.10 GB) plus Liquid's projector file mmproj-LFM3-Audio-2B-Q4_K_M.gguf (0.17 GB), from the Hub's file list. The repository also holds Q4_0, Q8_0, F16 and BF16 files" }, { "name": "LFM3-Audio-2B-MLX-4bit", "url": "https://huggingface.co/LiquidAI/LFM3-Audio-2B-MLX-4bit", "who": "publisher", "precision": "4bit", "sizeGB": 1.73, "memoryGB": 8, "format": "mlx", "runsOn": [ "MLX-VLM" ], "note": "Liquid also publishes 8-bit and BF16 MLX builds" }, { "name": "ollama lfm3-audio", "url": "https://ollama.com/library/lfm3-audio", "who": "ollama", "precision": "q4_k_m", "sizeGB": 1.7, "memoryGB": 8, "format": "ollama", "runsOn": [ "Ollama" ], "note": "Ollama's library build, size as its tags page shows it on 10 November 2026. The library also has q8_0, bf16, mxfp8 and nvfp4 tags" } ], "run": "llama-server -hf LiquidAI/LFM3-Audio-2B-GGUF:Q4_K_M --jinja", "runBuild": "LFM3-Audio-2B-GGUF Q4_K_M", "checked": "2026-11-10", "minMemoryGB": 8 }, "family": { "lab": "Liquid AI", "family": "LFM3", "url": "https://www.anchorterminal.com/open-weights/#liquid", "others": [ { "name": "LFM3-1.7B-Base", "url": "https://huggingface.co/LiquidAI/LFM3-1.7B-Base", "params": "1.73B" }, { "name": "LFM3-1.7B", "url": "https://huggingface.co/LiquidAI/LFM3-1.7B", "params": "1.73B", "listing": "https://www.anchorterminal.com/tools/lfm3-1-7b" }, { "name": "LFM3-VL-2B", "url": "https://huggingface.co/LiquidAI/LFM3-VL-2B", "params": "1.92B", "listing": "https://www.anchorterminal.com/tools/lfm3-vl-2b" }, { "name": "LFM3-Omni-2B", "url": "https://huggingface.co/LiquidAI/LFM3-Omni-2B", "params": "2.17B", "listing": "https://www.anchorterminal.com/tools/lfm3-omni-2b" } ] }, "area": "models", "provenance": { "legalEntity": "Liquid AI, Inc. (the licensor named in the LFM Open License)", "domain": "liquid.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/LiquidAI/LFM3-Audio-2B/commits/main", "securityTxt": "none", "checked": "2026-11-10", "notes": [ "The licence names Liquid AI, Inc. as licensor. The domain's registration date is as recorded on the liquid-d1 listing on 8 October 2026", "www.liquid.ai/.well-known/security.txt answered 404 on 10 November 2026" ], "score": 73 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/lfm3-audio-2b.json" }, "edges": [ { "by": 35, "category": "upkeep", "leads": "inkling", "name": "Documentation and upkeep", "reasons": { "a": "Model card 17 of 20, everything but a dated knowledge cut-off, counting Thinking Machines' own model card page. Training data 15, an EU training-content summary with sources, mix, a July 2026 collection cut-off and filtering. Last change 20, the weights files last changed on 23 July 2026, and Thinking Machines' Inkling renderer in tinker-cookbook changed on 30 October 2026, 3 days ago. Responsiveness 20, Thinking Machines answered 8 of the 12 questions and reports in its discussions. Version policy 5, a first release. File health 10, the files agree and the reports were answered.", "b": "Model card 17, Intended use (local agents, tool calling, structured outputs, fine-tuning), limitations (not recommended for agentic coding or complex multi-step reasoning, voice chat in English only), an architecture section, parameters (2B), context (32K) and 19 speech languages and locales. Training data 5, the card has no training section. Last change 20, the last commit, on 3 November 2026, changed the card's navigation icons, seven days before this check, and the one before it, on 31 October, edited the card. Responsiveness 0, Neither of the 2 discussions that aren't pull requests (27 and 31 October 2026) has a reply from a LiquidAI member. Version policy 5, LFM3 came out in new repositories and the LFM2.5 models stay in theirs. File health 5, the card gives a 32K context while config.json gives the language model 128,000 positions and Liquid's API lists 128,000 for the hosted model, so the card and the files don't agree on context. 17 + 5 + 20 + 0 + 5 + 5 = 52." }, "scores": { "a": 87, "b": 52 } }, { "by": 30, "category": "reach", "leads": "lfm3-audio-2b", "name": "Reach", "reasons": { "a": "Memory 0 of 30, the smallest 4-bit build is Thinking Machines' NVFP4 at 592.0 GB, about 710 GB with a fifth added, far above 256 GB. Runtimes 15, released Transformers, vLLM and SGLang run it, llama.cpp, Ollama and LM Studio don't. Builds 10, one quantised build (NVFP4). Terms 10, Apache 2.0 with a binding acceptable use policy on top, read as a custom licence. Download 10, no gate. Hosted 5, Together AI, Fireworks and DeepInfra are live on Hugging Face, and Thinking Machines' Tinker serves it too.", "b": "Memory 30, Liquid's Q4_K_M GGUF is 1.10 GB with its 0.17 GB projector file, and 1.27 GB × 1.2 = 1.5 GB, which fits 8 GB, well inside the 16 GB line. Runtimes 10, Released llama.cpp has the lfm3 architecture with the LFM3 audio projector and speech output (src/models/lfm3.cpp and tools/mtmd at b12242, with a realtime client example that starts this model), and Ollama's library has an lfm3-audio entry. Builds 15, Liquid's GGUF repository holds Q4_0, Q4_K_M, Q8_0, F16 and BF16 files, and Liquid publishes 4-bit and 8-bit MLX builds and an ONNX repository, all in the LiquidAI organisation. Terms 10, the LFM Open License v1.0, a custom licence that lets anyone use it commercially for free below a threshold of $10M annual revenue. Download 10, the Hub API reports gated false for the model and its GGUF, MLX and ONNX repositories on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, Liquid's own API lists lfm3-audio-2b among its models, so the publisher hosts it. 30 + 10 + 15 + 10 + 10 + 5 = 80." }, "scores": { "a": 50, "b": 80 } }, { "by": 30, "category": "risk", "leads": "inkling", "name": "Risk", "reasons": { "a": "File safety 25, safetensors only and no repository code to run. Provenance 15, the files are in the organisation Thinking Machines links to, with a SHA-256 on every LFS file. Safety evaluation 10, Thinking Machines' own StrongREJECT and FORTRESS results and commissioned external testers who published nothing. Agent guidance 10, the card says what its refusals miss and which safeguards to add, with nothing on prompt injection. Licence risk 5, 10 off for a use policy that reaches beyond the law and that can change at any time. Security programme 5, a security.txt and a disclosure policy, with public advisories unchecked and scored as absent.", "b": "File safety 15, safetensors only, no .bin, .pt or .pth files (25). Provenance 15, files in the LiquidAI organisation, which Liquid's docs page for the model and its blog post link to (10). Safety evaluation 0, no safety results on the card or in Liquid's blog post for the LFM3 family, neither of which mentions safety testing. Agent guidance 0, Nothing on prompt injection, an instruction hierarchy, what refusals cover or safeguards to add. Licence risk 10, 15 less 5 for the $10M annual revenue threshold on commercial use. Security programme 0, no way to report a flaw found. 15 + 15 + 0 + 0 + 10 + 0 = 40." }, "scores": { "a": 70, "b": 40 } } ], "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Thinking Machines Lab", "b": "Liquid 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": "LFM Open License v1.0 (free commercial use below $10M annual revenue)", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-07-23", "b": "2026-11-03", "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": "3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Inkling scores 64.7 (B) on agent readiness against LFM3-Audio-2B's 61 (C), and leads in 2 of 4 scored categories. LFM3-Audio-2B leads on reach.", "question": "Which is better for AI agents, Inkling or LFM3-Audio-2B?" } ], "goodFor": [ { "aheadOn": [ "Risk, 70 against 40", "Documentation and upkeep, 87 against 52" ], "also": null, "goodFor": "Agents calling a hosted open multimodal model with audio input, or teams with a multi-GPU datacentre node who want to run it themselves.", "slug": "inkling", "watchFor": "The smallest build Thinking Machines publishes needs about 710 GB, beyond any single workstation" }, { "aheadOn": [ "Reach, 80 against 50" ], "also": null, "goodFor": "Voice agents on a laptop or phone that need speech in, speech out and tool calls from one small model", "slug": "lfm3-audio-2b", "watchFor": "Only llama.cpp and Ollama run it in a release, though the card lists vLLM and SGLang" } ], "history": { "inkling": [ { "causes": [ "product" ], "date": "2026-11-02", "delta": 0.5, "from": 64.2, "fromGrade": "B", "to": 64.7, "toGrade": "B" } ], "lfm3-audio-2b": 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.json", "title": "Agents-A1-4B vs Inkling", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-lfm3-audio-2b.json", "title": "Agents-A1-4B vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-inkling.json", "title": "Apertus v1.5 8B vs Inkling", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-lfm3-audio-2b.json", "title": "Apertus v1.5 8B vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-inkling.json", "title": "Apodex-1.1-mini vs Inkling", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-lfm3-audio-2b.json", "title": "Apodex-1.1-mini vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/arete-27b-vs-inkling.json", "title": "Arete-27B vs Inkling", "url": "https://www.anchorterminal.com/compare/arete-27b-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/arete-27b-vs-lfm3-audio-2b.json", "title": "Arete-27B vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/arete-27b-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-inkling.json", "title": "BigBang-v1 vs Inkling", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-lfm3-audio-2b.json", "title": "BigBang-v1 vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-inkling.json", "title": "Carbon-X vs Inkling", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-lfm3-audio-2b.json", "title": "Carbon-X vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/cola2-vs-inkling.json", "title": "Cola2 vs Inkling", "url": "https://www.anchorterminal.com/compare/cola2-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/cola2-vs-lfm3-audio-2b.json", "title": "Cola2 vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/cola2-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-inkling.json", "title": "Cosmos-Reason2-2B vs Inkling", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-lfm3-audio-2b.json", "title": "Cosmos-Reason2-2B vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-inkling.json", "title": "Darwin-36B-Opus vs Inkling", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-lfm3-audio-2b.json", "title": "Darwin-36B-Opus vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling.json", "title": "DeepSeek-V3.2 vs Inkling", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-lfm3-audio-2b.json", "title": "DeepSeek-V3.2 vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-inkling.json", "title": "DeepSeek V4.1 Flash vs Inkling", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-lfm3-audio-2b.json", "title": "DeepSeek V4.1 Flash vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-inkling.json", "title": "DeepSeek-V4-Flash-0731 vs Inkling", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-lfm3-audio-2b.json", "title": "DeepSeek-V4-Flash-0731 vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling.json", "title": "Devstral Small 2 vs Inkling", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-audio-2b.json", "title": "Devstral Small 2 vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling.json", "title": "DiffusionGemma 26B A4B IT vs Inkling", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-lfm3-audio-2b.json", "title": "DiffusionGemma 26B A4B IT vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-inkling.json", "title": "EXAONE 4.5 33B vs Inkling", "url": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-lfm3-audio-2b.json", "title": "EXAONE 4.5 33B vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-inkling.json", "title": "Gemma 4 12B IT vs Inkling", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-lfm3-audio-2b.json", "title": "Gemma 4 12B IT vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-inkling.json", "title": "Gemma 4 26B A4B IT vs Inkling", "url": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-lfm3-audio-2b.json", "title": "Gemma 4 26B A4B IT vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-inkling.json", "title": "Gemma 4 31B IT vs Inkling", "url": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-lfm3-audio-2b.json", "title": "Gemma 4 31B IT vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-inkling.json", "title": "Gemma 4 E2B IT vs Inkling", "url": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-lfm3-audio-2b.json", "title": "Gemma 4 E2B IT vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-inkling.json", "title": "Gemma 4 E4B IT vs Inkling", "url": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-lfm3-audio-2b.json", "title": "Gemma 4 E4B IT vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-inkling.json", "title": "GLM-4.5-Air vs Inkling", "url": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-lfm3-audio-2b.json", "title": "GLM-4.5-Air vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-inkling.json", "title": "GLM-4.7-Flash vs Inkling", "url": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-lfm3-audio-2b.json", "title": "GLM-4.7-Flash vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling.json", "title": "GLM-5.3-Flash vs Inkling", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm3-audio-2b.json", "title": "GLM-5.3-Flash vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-inkling.json", "title": "GLM-5.3 vs Inkling", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-lfm3-audio-2b.json", "title": "GLM-5.3 vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-inkling.json", "title": "gpt-oss-120b vs Inkling", "url": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-lfm3-audio-2b.json", "title": "gpt-oss-120b vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling.json", "title": "gpt-oss-20b vs Inkling", "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm3-audio-2b.json", "title": "gpt-oss-20b vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-30b-vs-inkling.json", "title": "Granite 4.2 30B vs Inkling", "url": "https://www.anchorterminal.com/compare/granite-4-2-30b-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-30b-vs-lfm3-audio-2b.json", "title": "Granite 4.2 30B vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/granite-4-2-30b-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-inkling.json", "title": "Granite 4.2 3B vs Inkling", "url": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-lfm3-audio-2b.json", "title": "Granite 4.2 3B vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-8b-vs-inkling.json", "title": "Granite 4.2 8B vs Inkling", "url": "https://www.anchorterminal.com/compare/granite-4-2-8b-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-8b-vs-lfm3-audio-2b.json", "title": "Granite 4.2 8B vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/granite-4-2-8b-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-inkling.json", "title": "Hy-Memory-30B-A3B vs Inkling", "url": "https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-lfm3-audio-2b.json", "title": "Hy-Memory-30B-A3B vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-inkling.json", "title": "Hy3 vs Inkling", "url": "https://www.anchorterminal.com/compare/hy3-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-lfm3-audio-2b.json", "title": "Hy3 vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/hy3-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/inkling-small-vs-lfm3-audio-2b.json", "title": "Inkling-Small vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/inkling-small-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-inkling-small.json", "title": "Inkling vs Inkling-Small", "url": "https://www.anchorterminal.com/compare/inkling-vs-inkling-small" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-internvl3-5-gpt-oss-20b-a4b-preview.json", "title": "Inkling vs InternVL3.5-GPT-OSS-20B-A4B-Preview", "url": "https://www.anchorterminal.com/compare/inkling-vs-internvl3-5-gpt-oss-20b-a4b-preview" }, { "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/inkling-vs-kimi-k3-1-pro.json", "title": "Inkling vs Kimi K3.1 Pro", "url": "https://www.anchorterminal.com/compare/inkling-vs-kimi-k3-1-pro" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-kolibri-1.json", "title": "Inkling vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/inkling-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-kronos.json", "title": "Inkling vs Kronos", "url": "https://www.anchorterminal.com/compare/inkling-vs-kronos" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-laguna-m-1.json", "title": "Inkling vs Laguna M.1", "url": "https://www.anchorterminal.com/compare/inkling-vs-laguna-m-1" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-laguna-s-2-1.json", "title": "Inkling vs Laguna S 2.1", "url": "https://www.anchorterminal.com/compare/inkling-vs-laguna-s-2-1" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-laguna-xs-2-1.json", "title": "Inkling vs Laguna XS 2.1", "url": "https://www.anchorterminal.com/compare/inkling-vs-laguna-xs-2-1" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-lbs-27b.json", "title": "Inkling vs LBS-27B", "url": "https://www.anchorterminal.com/compare/inkling-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-lfm2-5-2-6b.json", "title": "Inkling vs LFM2.5-2.6B", "url": "https://www.anchorterminal.com/compare/inkling-vs-lfm2-5-2-6b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-lfm3-1-7b.json", "title": "Inkling vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/inkling-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-lfm3-omni-2b.json", "title": "Inkling vs LFM3-Omni-2B", "url": "https://www.anchorterminal.com/compare/inkling-vs-lfm3-omni-2b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-lfm3-vl-2b.json", "title": "Inkling vs LFM3-VL-2B", "url": "https://www.anchorterminal.com/compare/inkling-vs-lfm3-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-ling-3-0-tiny.json", "title": "Inkling vs Ling-3.0-tiny", "url": "https://www.anchorterminal.com/compare/inkling-vs-ling-3-0-tiny" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-ling-3-1-flash-1019.json", "title": "Inkling vs Ling-3.1-flash-1019", "url": "https://www.anchorterminal.com/compare/inkling-vs-ling-3-1-flash-1019" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-longcat-2-5.json", "title": "Inkling vs LongCat-2.5", "url": "https://www.anchorterminal.com/compare/inkling-vs-longcat-2-5" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-mimo-v2-6-distill-qwen-9b.json", "title": "Inkling vs MiMo-V2.6 Distill Qwen 9B", "url": "https://www.anchorterminal.com/compare/inkling-vs-mimo-v2-6-distill-qwen-9b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-mimo-v2-6-flash-rl.json", "title": "Inkling vs MiMo-V2.6-Flash-RL", "url": "https://www.anchorterminal.com/compare/inkling-vs-mimo-v2-6-flash-rl" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-minicpm-o-4-5.json", "title": "Inkling vs MiniCPM-o 4.5", "url": "https://www.anchorterminal.com/compare/inkling-vs-minicpm-o-4-5" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-minicpm-v-4-7-1b.json", "title": "Inkling vs MiniCPM-V 4.7 1B", "url": "https://www.anchorterminal.com/compare/inkling-vs-minicpm-v-4-7-1b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-minicpm-v-4-7-35b-a3b.json", "title": "Inkling vs MiniCPM-V 4.7 35B-A3B", "url": "https://www.anchorterminal.com/compare/inkling-vs-minicpm-v-4-7-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-minicpm5-2b.json", "title": "Inkling vs MiniCPM5-2B", "url": "https://www.anchorterminal.com/compare/inkling-vs-minicpm5-2b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-minimax-m2-5.json", "title": "Inkling vs MiniMax-M2.5", "url": "https://www.anchorterminal.com/compare/inkling-vs-minimax-m2-5" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-minimax-m2-7.json", "title": "Inkling vs MiniMax-M2.7", "url": "https://www.anchorterminal.com/compare/inkling-vs-minimax-m2-7" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-minimax-m3-1-flash.json", "title": "Inkling vs MiniMax-M3.1-Flash", "url": "https://www.anchorterminal.com/compare/inkling-vs-minimax-m3-1-flash" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-mistral-large-4.json", "title": "Inkling vs Mistral Large 4", "url": "https://www.anchorterminal.com/compare/inkling-vs-mistral-large-4" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-muse-glimmer-30b.json", "title": "Inkling vs Muse Glimmer 30B", "url": "https://www.anchorterminal.com/compare/inkling-vs-muse-glimmer-30b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-nanbeige-4-2-3b.json", "title": "Inkling vs Nanbeige4.2-3B", "url": "https://www.anchorterminal.com/compare/inkling-vs-nanbeige-4-2-3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-nanbeige-4-3-33b.json", "title": "Inkling vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/inkling-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-5-bolt-e4b-4gb.json", "title": "Inkling vs NVIDIA Nemotron 3.5 Bolt E4B 4GB", "url": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-5-bolt-e4b-4gb" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-5-lightning-30b-a3b.json", "title": "Inkling vs Nemotron 3.5 Lightning 30B A3B", "url": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-5-lightning-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-nano-30b-a3b.json", "title": "Inkling vs Nemotron 3 Nano 30B A3B", "url": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-nano-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-nano-4b.json", "title": "Inkling vs Nemotron 3 Nano 4B", "url": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-nano-4b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "Inkling vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-super-120b-a12b.json", "title": "Inkling vs Nemotron 3 Super 120B A12B", "url": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-super-120b-a12b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-ultra-550b-a55b.json", "title": "Inkling vs Nemotron 3 Ultra 550B A55B", "url": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-ultra-550b-a55b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-north-mini-code-1-0.json", "title": "Inkling vs North Mini Code 1.0", "url": "https://www.anchorterminal.com/compare/inkling-vs-north-mini-code-1-0" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-occamy-1-0.json", "title": "Inkling vs occamy-1.0", "url": "https://www.anchorterminal.com/compare/inkling-vs-occamy-1-0" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-olmo-3-7b-think.json", "title": "Inkling vs Olmo 3 7B Think", "url": "https://www.anchorterminal.com/compare/inkling-vs-olmo-3-7b-think" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-122b.json", "title": "Inkling vs Ornith-1.5-122B", "url": "https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-122b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-35b-a3b.json", "title": "Inkling vs Ornith-1.5-35B-A3B", "url": "https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-397b.json", "title": "Inkling vs Ornith-1.5-397B", "url": "https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-397b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-9b.json", "title": "Inkling vs Ornith-1.5-9B", "url": "https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-9b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-otel-2-0-llm-31b-it.json", "title": "Inkling vs OTel-2.0-LLM-31B-IT", "url": "https://www.anchorterminal.com/compare/inkling-vs-otel-2-0-llm-31b-it" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen-agentworld-35b-a3b.json", "title": "Inkling vs Qwen-AgentWorld-35B-A3B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen-agentworld-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-30b-a3b-instruct-2507.json", "title": "Inkling vs Qwen3-30B-A3B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-30b-a3b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-4b-instruct-2507.json", "title": "Inkling vs Qwen3-4B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-4b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-0-8b.json", "title": "Inkling vs Qwen3.5-0.8B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-0-8b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-122b-a10b.json", "title": "Inkling vs Qwen3.5-122B-A10B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-122b-a10b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-2b.json", "title": "Inkling vs Qwen3.5-2B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-2b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-397b-a17b.json", "title": "Inkling vs Qwen3.5-397B-A17B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-397b-a17b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-4b.json", "title": "Inkling vs Qwen3.5-4B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-4b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-9b.json", "title": "Inkling vs Qwen3.5-9B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-9b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-6-27b.json", "title": "Inkling vs Qwen3.6-27B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-6-27b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-6-35b-a3b.json", "title": "Inkling vs Qwen3.6-35B-A3B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-6-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-8-27b.json", "title": "Inkling vs Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-8-flash-next.json", "title": "Inkling vs Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-coder-30b-a3b-instruct.json", "title": "Inkling vs Qwen3-Coder-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-coder-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-coder-next.json", "title": "Inkling vs Qwen3-Coder-Next", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-coder-next" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-omni-30b-a3b-instruct.json", "title": "Inkling vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-2b-instruct.json", "title": "Inkling vs Qwen3-VL-2B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-2b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-30b-a3b-instruct.json", "title": "Inkling vs Qwen3-VL-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-32b-instruct.json", "title": "Inkling vs Qwen3-VL-32B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-32b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-4b-instruct.json", "title": "Inkling vs Qwen3-VL-4B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-4b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-8b-instruct.json", "title": "Inkling vs Qwen3-VL-8B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-8b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwopus3-8-27b-flash-v2.json", "title": "Inkling vs Qwopus3.8-27B-Flash-V2", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwopus3-8-27b-flash-v2" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-recursive-flint.json", "title": "Inkling vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/inkling-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-ripple-65b-preview.json", "title": "Inkling vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/inkling-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-sensenova-loop-9b-preview.json", "title": "Inkling vs SenseNova-Loop-9B-Preview", "url": "https://www.anchorterminal.com/compare/inkling-vs-sensenova-loop-9b-preview" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-smollm3-3b.json", "title": "Inkling vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/inkling-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-spark-x2-6-4b.json", "title": "Inkling vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/inkling-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-step-3-7-flash.json", "title": "Inkling vs Step 3.7 Flash", "url": "https://www.anchorterminal.com/compare/inkling-vs-step-3-7-flash" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-swift-1-5-qwen3-8-27b.json", "title": "Inkling vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/inkling-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-swift-1-5-qwen3-8-flash-next.json", "title": "Inkling vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/inkling-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-thinkingcap-qwen3-8-27b.json", "title": "Inkling vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/inkling-vs-thinkingcap-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-unlimited-ocr-2.json", "title": "Inkling vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/inkling-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-wevisone-vl-2b.json", "title": "Inkling vs WeVisOne-VL-2B", "url": "https://www.anchorterminal.com/compare/inkling-vs-wevisone-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-wevisone-vl-4b.json", "title": "Inkling vs WeVisOne-VL-4B", "url": "https://www.anchorterminal.com/compare/inkling-vs-wevisone-vl-4b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-zaya1-8b.json", "title": "Inkling vs ZAYA1-8B", "url": "https://www.anchorterminal.com/compare/inkling-vs-zaya1-8b" }, { "json": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-lfm3-audio-2b.json", "title": "InternVL3.5-GPT-OSS-20B-A4B-Preview vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-1-pro-vs-lfm3-audio-2b.json", "title": "Kimi K3.1 Pro vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/kimi-k3-1-pro-vs-lfm3-audio-2b" }, { "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/kolibri-1-vs-lfm3-audio-2b.json", "title": "Kolibri-1 vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/kronos-vs-lfm3-audio-2b.json", "title": "Kronos vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/kronos-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/laguna-m-1-vs-lfm3-audio-2b.json", "title": "Laguna M.1 vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/laguna-m-1-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/laguna-s-2-1-vs-lfm3-audio-2b.json", "title": "Laguna S 2.1 vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/laguna-s-2-1-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-lfm3-audio-2b.json", "title": "Laguna XS 2.1 vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-lfm3-audio-2b.json", "title": "LBS-27B vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-lfm3-audio-2b.json", "title": "LFM2.5-2.6B vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-lfm3-audio-2b.json", "title": "LFM3-1.7B vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-lfm3-omni-2b.json", "title": "LFM3-Audio-2B vs LFM3-Omni-2B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-lfm3-omni-2b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-lfm3-vl-2b.json", "title": "LFM3-Audio-2B vs LFM3-VL-2B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-lfm3-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ling-3-0-tiny.json", "title": "LFM3-Audio-2B vs Ling-3.0-tiny", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ling-3-0-tiny" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ling-3-1-flash-1019.json", "title": "LFM3-Audio-2B vs Ling-3.1-flash-1019", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ling-3-1-flash-1019" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-longcat-2-5.json", "title": "LFM3-Audio-2B vs LongCat-2.5", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-longcat-2-5" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-mimo-v2-6-distill-qwen-9b.json", "title": "LFM3-Audio-2B vs MiMo-V2.6 Distill Qwen 9B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-mimo-v2-6-distill-qwen-9b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-mimo-v2-6-flash-rl.json", "title": "LFM3-Audio-2B vs MiMo-V2.6-Flash-RL", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-mimo-v2-6-flash-rl" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minicpm-o-4-5.json", "title": "LFM3-Audio-2B vs MiniCPM-o 4.5", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minicpm-o-4-5" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minicpm-v-4-7-1b.json", "title": "LFM3-Audio-2B vs MiniCPM-V 4.7 1B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minicpm-v-4-7-1b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minicpm-v-4-7-35b-a3b.json", "title": "LFM3-Audio-2B vs MiniCPM-V 4.7 35B-A3B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minicpm-v-4-7-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minicpm5-2b.json", "title": "LFM3-Audio-2B vs MiniCPM5-2B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minicpm5-2b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minimax-m2-5.json", "title": "LFM3-Audio-2B vs MiniMax-M2.5", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minimax-m2-5" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minimax-m2-7.json", "title": "LFM3-Audio-2B vs MiniMax-M2.7", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minimax-m2-7" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minimax-m3-1-flash.json", "title": "LFM3-Audio-2B vs MiniMax-M3.1-Flash", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minimax-m3-1-flash" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-mistral-large-4.json", "title": "LFM3-Audio-2B vs Mistral Large 4", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-mistral-large-4" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-muse-glimmer-30b.json", "title": "LFM3-Audio-2B vs Muse Glimmer 30B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-muse-glimmer-30b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nanbeige-4-2-3b.json", "title": "LFM3-Audio-2B vs Nanbeige4.2-3B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nanbeige-4-2-3b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nanbeige-4-3-33b.json", "title": "LFM3-Audio-2B vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-5-bolt-e4b-4gb.json", "title": "LFM3-Audio-2B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-5-bolt-e4b-4gb" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-5-lightning-30b-a3b.json", "title": "LFM3-Audio-2B vs Nemotron 3.5 Lightning 30B A3B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-5-lightning-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-nano-30b-a3b.json", "title": "LFM3-Audio-2B vs Nemotron 3 Nano 30B A3B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-nano-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-nano-4b.json", "title": "LFM3-Audio-2B vs Nemotron 3 Nano 4B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-nano-4b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "LFM3-Audio-2B vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-super-120b-a12b.json", "title": "LFM3-Audio-2B vs Nemotron 3 Super 120B A12B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-super-120b-a12b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-ultra-550b-a55b.json", "title": "LFM3-Audio-2B vs Nemotron 3 Ultra 550B A55B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-ultra-550b-a55b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-north-mini-code-1-0.json", "title": "LFM3-Audio-2B vs North Mini Code 1.0", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-north-mini-code-1-0" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-occamy-1-0.json", "title": "LFM3-Audio-2B vs occamy-1.0", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-occamy-1-0" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-olmo-3-7b-think.json", "title": "LFM3-Audio-2B vs Olmo 3 7B Think", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-olmo-3-7b-think" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ornith-1-5-122b.json", "title": "LFM3-Audio-2B vs Ornith-1.5-122B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ornith-1-5-122b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ornith-1-5-35b-a3b.json", "title": "LFM3-Audio-2B vs Ornith-1.5-35B-A3B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ornith-1-5-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ornith-1-5-397b.json", "title": "LFM3-Audio-2B vs Ornith-1.5-397B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ornith-1-5-397b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ornith-1-5-9b.json", "title": "LFM3-Audio-2B vs Ornith-1.5-9B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ornith-1-5-9b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-otel-2-0-llm-31b-it.json", "title": "LFM3-Audio-2B vs OTel-2.0-LLM-31B-IT", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-otel-2-0-llm-31b-it" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen-agentworld-35b-a3b.json", "title": "LFM3-Audio-2B vs Qwen-AgentWorld-35B-A3B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen-agentworld-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-30b-a3b-instruct-2507.json", "title": "LFM3-Audio-2B vs Qwen3-30B-A3B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-30b-a3b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-4b-instruct-2507.json", "title": "LFM3-Audio-2B vs Qwen3-4B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-4b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-5-0-8b.json", "title": "LFM3-Audio-2B vs Qwen3.5-0.8B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-5-0-8b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-5-122b-a10b.json", "title": "LFM3-Audio-2B vs Qwen3.5-122B-A10B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-5-122b-a10b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-5-2b.json", "title": "LFM3-Audio-2B vs Qwen3.5-2B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-5-2b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-5-397b-a17b.json", "title": "LFM3-Audio-2B vs Qwen3.5-397B-A17B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-5-397b-a17b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-5-4b.json", "title": "LFM3-Audio-2B vs Qwen3.5-4B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-5-4b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-5-9b.json", "title": "LFM3-Audio-2B vs Qwen3.5-9B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-5-9b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-6-27b.json", "title": "LFM3-Audio-2B vs Qwen3.6-27B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-6-27b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-6-35b-a3b.json", "title": "LFM3-Audio-2B vs Qwen3.6-35B-A3B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-6-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-8-27b.json", "title": "LFM3-Audio-2B vs Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-8-flash-next.json", "title": "LFM3-Audio-2B vs Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-coder-30b-a3b-instruct.json", "title": "LFM3-Audio-2B vs Qwen3-Coder-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-coder-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-coder-next.json", "title": "LFM3-Audio-2B vs Qwen3-Coder-Next", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-coder-next" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-omni-30b-a3b-instruct.json", "title": "LFM3-Audio-2B vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-vl-2b-instruct.json", "title": "LFM3-Audio-2B vs Qwen3-VL-2B-Instruct", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-vl-2b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-vl-30b-a3b-instruct.json", "title": "LFM3-Audio-2B vs Qwen3-VL-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-vl-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-vl-32b-instruct.json", "title": "LFM3-Audio-2B vs Qwen3-VL-32B-Instruct", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-vl-32b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-vl-4b-instruct.json", "title": "LFM3-Audio-2B vs Qwen3-VL-4B-Instruct", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-vl-4b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-vl-8b-instruct.json", "title": "LFM3-Audio-2B vs Qwen3-VL-8B-Instruct", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-vl-8b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwopus3-8-27b-flash-v2.json", "title": "LFM3-Audio-2B vs Qwopus3.8-27B-Flash-V2", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwopus3-8-27b-flash-v2" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-recursive-flint.json", "title": "LFM3-Audio-2B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ripple-65b-preview.json", "title": "LFM3-Audio-2B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-sensenova-loop-9b-preview.json", "title": "LFM3-Audio-2B vs SenseNova-Loop-9B-Preview", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-sensenova-loop-9b-preview" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-smollm3-3b.json", "title": "LFM3-Audio-2B vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-spark-x2-6-4b.json", "title": "LFM3-Audio-2B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-step-3-7-flash.json", "title": "LFM3-Audio-2B vs Step 3.7 Flash", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-step-3-7-flash" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-swift-1-5-qwen3-8-27b.json", "title": "LFM3-Audio-2B vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-swift-1-5-qwen3-8-flash-next.json", "title": "LFM3-Audio-2B vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-thinkingcap-qwen3-8-27b.json", "title": "LFM3-Audio-2B vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-thinkingcap-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-unlimited-ocr-2.json", "title": "LFM3-Audio-2B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-wevisone-vl-2b.json", "title": "LFM3-Audio-2B vs WeVisOne-VL-2B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-wevisone-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-wevisone-vl-4b.json", "title": "LFM3-Audio-2B vs WeVisOne-VL-4B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-wevisone-vl-4b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-zaya1-8b.json", "title": "LFM3-Audio-2B vs ZAYA1-8B", "url": "https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-zaya1-8b" } ], "panel": null, "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 30, "edge": "lfm3-audio-2b", "inkling": 50, "key": "reach", "lfm3-audio-2b": 80, "name": "Reach", "weight": 25 }, { "by": 30, "edge": "inkling", "inkling": 70, "key": "risk", "lfm3-audio-2b": 40, "name": "Risk", "weight": 20 }, { "by": 0, "edge": "", "inkling": 85, "key": "interface", "lfm3-audio-2b": 85, "name": "Agent interface", "weight": 10 }, { "by": 35, "edge": "inkling", "inkling": 87, "key": "upkeep", "lfm3-audio-2b": 52, "name": "Documentation and upkeep", "weight": 10 } ], "summary": "Inkling scores 64.7 (B) on agent readiness against LFM3-Audio-2B's 61 (C), and leads in 2 of 4 scored categories. LFM3-Audio-2B leads on reach. Both do open-weight models you run yourself.", "tasks": null, "tutorials": [], "verdicts": { "inkling": "Thinking Machines' large multimodal generalist, stronger than Inkling-Small on factual recall by its own numbers. It needs about 710 GB of datacentre GPU memory even in NVFP4, so most agents will use a host such as Together AI or Tinker. The main risks are a use policy that binds on download and can change, and no outside safety results.", "lfm3-audio-2b": "A 2B model that listens and speaks on an 8 GB machine, transcribes and translates 19 languages and turns spoken requests into tool calls. Only llama.cpp and Ollama run it in a release. The context is 32K, voice chat is English only, Liquid hasn't answered the repository's questions, and there are no safety results or data sources." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/inkling-vs-lfm3-audio-2b", "json": "https://www.anchorterminal.com/compare/inkling-vs-lfm3-audio-2b.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/inkling-vs-lfm3-audio-2b.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/inkling-vs-lfm3-audio-2b.min.md" }, "markdown": "Inkling scores 64.7 (B) on agent readiness against LFM3-Audio-2B's 61 (C), and leads in 2 of 4 scored categories. LFM3-Audio-2B leads on reach. Both do open-weight models you run yourself.\n\n- Inkling: grade B, 64.7/100, rank #19 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/inkling.md · JSON https://www.anchorterminal.com/api/v1/tools/inkling.json\n- LFM3-Audio-2B: grade C, 61/100, rank #70 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/lfm3-audio-2b.md · JSON https://www.anchorterminal.com/api/v1/tools/lfm3-audio-2b.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 6359 open weights comparisons: https://www.anchorterminal.com/compare/open-weights/index.md\n\n## Which one, for what\n\n### Inkling (B)\n\nGood for: Agents calling a hosted open multimodal model with audio input, or teams with a multi-GPU datacentre node who want to run it themselves.\n\nAhead on:\n- Risk, 70 against 40\n- Documentation and upkeep, 87 against 52\n\nWatch for: The smallest build Thinking Machines publishes needs about 710 GB, beyond any single workstation\n\n### LFM3-Audio-2B (C)\n\nGood for: Voice agents on a laptop or phone that need speech in, speech out and tool calls from one small model\n\nAhead on:\n- Reach, 80 against 50\n\nWatch for: Only llama.cpp and Ollama run it in a release, though the card lists vLLM and SGLang\n\n\n## Why the edge\n\n### Documentation and upkeep: Inkling +35\n\n- Inkling (87): Model card 17 of 20, everything but a dated knowledge cut-off, counting Thinking Machines' own model card page. Training data 15, an EU training-content summary with sources, mix, a July 2026 collection cut-off and filtering. Last change 20, the weights files last changed on 23 July 2026, and Thinking Machines' Inkling renderer in tinker-cookbook changed on 30 October 2026, 3 days ago. Responsiveness 20, Thinking Machines answered 8 of the 12 questions and reports in its discussions. Version policy 5, a first release. File health 10, the files agree and the reports were answered.\n- LFM3-Audio-2B (52): Model card 17, Intended use (local agents, tool calling, structured outputs, fine-tuning), limitations (not recommended for agentic coding or complex multi-step reasoning, voice chat in English only), an architecture section, parameters (2B), context (32K) and 19 speech languages and locales. Training data 5, the card has no training section. Last change 20, the last commit, on 3 November 2026, changed the card's navigation icons, seven days before this check, and the one before it, on 31 October, edited the card. Responsiveness 0, Neither of the 2 discussions that aren't pull requests (27 and 31 October 2026) has a reply from a LiquidAI member. Version policy 5, LFM3 came out in new repositories and the LFM2.5 models stay in theirs. File health 5, the card gives a 32K context while config.json gives the language model 128,000 positions and Liquid's API lists 128,000 for the hosted model, so the card and the files don't agree on context. 17 + 5 + 20 + 0 + 5 + 5 = 52.\n\n### Reach: LFM3-Audio-2B +30\n\n- Inkling (50): Memory 0 of 30, the smallest 4-bit build is Thinking Machines' NVFP4 at 592.0 GB, about 710 GB with a fifth added, far above 256 GB. Runtimes 15, released Transformers, vLLM and SGLang run it, llama.cpp, Ollama and LM Studio don't. Builds 10, one quantised build (NVFP4). Terms 10, Apache 2.0 with a binding acceptable use policy on top, read as a custom licence. Download 10, no gate. Hosted 5, Together AI, Fireworks and DeepInfra are live on Hugging Face, and Thinking Machines' Tinker serves it too.\n- LFM3-Audio-2B (80): Memory 30, Liquid's Q4_K_M GGUF is 1.10 GB with its 0.17 GB projector file, and 1.27 GB × 1.2 = 1.5 GB, which fits 8 GB, well inside the 16 GB line. Runtimes 10, Released llama.cpp has the lfm3 architecture with the LFM3 audio projector and speech output (src/models/lfm3.cpp and tools/mtmd at b12242, with a realtime client example that starts this model), and Ollama's library has an lfm3-audio entry. Builds 15, Liquid's GGUF repository holds Q4_0, Q4_K_M, Q8_0, F16 and BF16 files, and Liquid publishes 4-bit and 8-bit MLX builds and an ONNX repository, all in the LiquidAI organisation. Terms 10, the LFM Open License v1.0, a custom licence that lets anyone use it commercially for free below a threshold of $10M annual revenue. Download 10, the Hub API reports gated false for the model and its GGUF, MLX and ONNX repositories on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, Liquid's own API lists lfm3-audio-2b among its models, so the publisher hosts it. 30 + 10 + 15 + 10 + 10 + 5 = 80.\n\n### Risk: Inkling +30\n\n- Inkling (70): File safety 25, safetensors only and no repository code to run. Provenance 15, the files are in the organisation Thinking Machines links to, with a SHA-256 on every LFS file. Safety evaluation 10, Thinking Machines' own StrongREJECT and FORTRESS results and commissioned external testers who published nothing. Agent guidance 10, the card says what its refusals miss and which safeguards to add, with nothing on prompt injection. Licence risk 5, 10 off for a use policy that reaches beyond the law and that can change at any time. Security programme 5, a security.txt and a disclosure policy, with public advisories unchecked and scored as absent.\n- LFM3-Audio-2B (40): File safety 15, safetensors only, no .bin, .pt or .pth files (25). Provenance 15, files in the LiquidAI organisation, which Liquid's docs page for the model and its blog post link to (10). Safety evaluation 0, no safety results on the card or in Liquid's blog post for the LFM3 family, neither of which mentions safety testing. Agent guidance 0, Nothing on prompt injection, an instruction hierarchy, what refusals cover or safeguards to add. Licence risk 10, 15 less 5 for the $10M annual revenue threshold on commercial use. Security programme 0, no way to report a flaw found. 15 + 15 + 0 + 0 + 10 + 0 = 40.\n\n## Score by category\n\n| Category | Weight | Inkling | LFM3-Audio-2B | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 50 | 80 | LFM3-Audio-2B +30 |\n| Risk | 20% (20 this run) | 70 | 40 | Inkling +30 |\n| Agent interface | 10% (10 this run) | 85 | 85 | even |\n| Documentation and upkeep | 10% (10 this run) | 87 | 52 | Inkling +35 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **64.7 · B** | **61 · C** | |\n\n## Facts side by side\n\n| Fact | Inkling | LFM3-Audio-2B |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Thinking Machines Lab | Liquid 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 | LFM Open License v1.0 (free commercial use below $10M annual revenue) |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-07-23 | 2026-11-03 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Agent reviews | 3/5 (4) | none |\n\n## How the scores have moved\n\n### Inkling\n\n- +0.5 on 2 November 2026: product\n\n### LFM3-Audio-2B\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Inkling.** Thinking Machines' large multimodal generalist, stronger than Inkling-Small on factual recall by its own numbers. It needs about 710 GB of datacentre GPU memory even in NVFP4, so most agents will use a host such as Together AI or Tinker. The main risks are a use policy that binds on download and can change, and no outside safety results.\n\n**LFM3-Audio-2B.** A 2B model that listens and speaks on an 8 GB machine, transcribes and translates 19 languages and turns spoken requests into tool calls. Only llama.cpp and Ollama run it in a release. The context is 32K, voice chat is English only, Liquid hasn't answered the repository's questions, and there are no safety results or data sources.\n\n## Before you call either\n\n### Inkling\n\n1. Unless you have a multi-GPU Blackwell or H200 node, call it through Together AI, Fireworks, DeepInfra or Tinker rather than starting it\n2. On 8 B200 GPUs, SGLang's recipe is `sglang serve --trust-remote-code --model-path thinkingmachines/Inkling-NVFP4 --tp 8 --quantization modelopt_fp4 --enable-multimodal --reasoning-parser inkling --tool-call-parser inkling`\n3. Use the inkling tool parser, not Hermes, and the inkling reasoning parser\n4. Pass `reasoning_effort` as none, minimal, low, medium, high (the default) or max, or a number from 0 to 0.99. The repository's template has no xhigh preset and raises an error for it, though Thinking Machines' docs list xhigh\n5. Tool call arguments must reach the template as an object, not a JSON string, or it raises an error\n6. Audio should be 16 kHz WAV, ideally under 20 minutes, and images 40 to 4096 px a side, per the card\n7. Read the Model Acceptable Use Policy before deploying, it binds on download and bars some uses that are legal\n\n### LFM3-Audio-2B\n\n1. Start it with `llama-server -hf LiquidAI/LFM3-Audio-2B-GGUF:Q4_K_M --jinja` or `ollama run lfm3-audio`\n2. llama.cpp ships examples/realtime_client.py for live speech with this model\n3. Prefill the assistant turn with an open think tag to let it reason before a text reply\n4. The context is 32K\n5. Voice chat is English only, while transcription, synthesis and translation cover 19 languages and locales\n6. Liquid doesn't recommend it for agentic coding or complex multi-step reasoning\n\n## Questions\n\n### Which is better for AI agents, Inkling or LFM3-Audio-2B?\n\nInkling scores 64.7 (B) on agent readiness against LFM3-Audio-2B's 61 (C), and leads in 2 of 4 scored categories. LFM3-Audio-2B leads on reach.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/inkling-vs-lfm3-audio-2b.json, and with the fewest tokens: https://www.anchorterminal.com/compare/inkling-vs-lfm3-audio-2b.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"inkling\", \"b\": \"lfm3-audio-2b\"}`. From a terminal: `anchor compare inkling lfm3-audio-2b`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/inkling.json and https://www.anchorterminal.com/api/v1/tools/lfm3-audio-2b.json\n\n## Other comparisons with Inkling or LFM3-Audio-2B\n\n- [Agents-A1-4B vs Inkling](https://www.anchorterminal.com/compare/agents-a1-4b-vs-inkling.md)\n- [Agents-A1-4B vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/agents-a1-4b-vs-lfm3-audio-2b.md)\n- [Apertus v1.5 8B vs Inkling](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-inkling.md)\n- [Apertus v1.5 8B vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-lfm3-audio-2b.md)\n- [Apodex-1.1-mini vs Inkling](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-inkling.md)\n- [Apodex-1.1-mini vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-lfm3-audio-2b.md)\n- [Arete-27B vs Inkling](https://www.anchorterminal.com/compare/arete-27b-vs-inkling.md)\n- [Arete-27B vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/arete-27b-vs-lfm3-audio-2b.md)\n- [BigBang-v1 vs Inkling](https://www.anchorterminal.com/compare/bigbang-v1-vs-inkling.md)\n- [BigBang-v1 vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/bigbang-v1-vs-lfm3-audio-2b.md)\n- [Carbon-X vs Inkling](https://www.anchorterminal.com/compare/carbon-x-vs-inkling.md)\n- [Carbon-X vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/carbon-x-vs-lfm3-audio-2b.md)\n- [Cola2 vs Inkling](https://www.anchorterminal.com/compare/cola2-vs-inkling.md)\n- [Cola2 vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/cola2-vs-lfm3-audio-2b.md)\n- [Cosmos-Reason2-2B vs Inkling](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-inkling.md)\n- [Cosmos-Reason2-2B vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-lfm3-audio-2b.md)\n- [Darwin-36B-Opus vs Inkling](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-inkling.md)\n- [Darwin-36B-Opus vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-lfm3-audio-2b.md)\n- [DeepSeek-V3.2 vs Inkling](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling.md)\n- [DeepSeek-V3.2 vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-lfm3-audio-2b.md)\n- [DeepSeek V4.1 Flash vs Inkling](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-inkling.md)\n- [DeepSeek V4.1 Flash vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-lfm3-audio-2b.md)\n- [DeepSeek-V4-Flash-0731 vs Inkling](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-inkling.md)\n- [DeepSeek-V4-Flash-0731 vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-lfm3-audio-2b.md)\n- [Devstral Small 2 vs Inkling](https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling.md)\n- [Devstral Small 2 vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-audio-2b.md)\n- [DiffusionGemma 26B A4B IT vs Inkling](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling.md)\n- [DiffusionGemma 26B A4B IT vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-lfm3-audio-2b.md)\n- [EXAONE 4.5 33B vs Inkling](https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-inkling.md)\n- [EXAONE 4.5 33B vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-lfm3-audio-2b.md)\n- [Gemma 4 12B IT vs Inkling](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-inkling.md)\n- [Gemma 4 12B IT vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-lfm3-audio-2b.md)\n- [Gemma 4 26B A4B IT vs Inkling](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-inkling.md)\n- [Gemma 4 26B A4B IT vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-lfm3-audio-2b.md)\n- [Gemma 4 31B IT vs Inkling](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-inkling.md)\n- [Gemma 4 31B IT vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-lfm3-audio-2b.md)\n- [Gemma 4 E2B IT vs Inkling](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-inkling.md)\n- [Gemma 4 E2B IT vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-lfm3-audio-2b.md)\n- [Gemma 4 E4B IT vs Inkling](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-inkling.md)\n- [Gemma 4 E4B IT vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-lfm3-audio-2b.md)\n- [GLM-4.5-Air vs Inkling](https://www.anchorterminal.com/compare/glm-4-5-air-vs-inkling.md)\n- [GLM-4.5-Air vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/glm-4-5-air-vs-lfm3-audio-2b.md)\n- [GLM-4.7-Flash vs Inkling](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-inkling.md)\n- [GLM-4.7-Flash vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-lfm3-audio-2b.md)\n- [GLM-5.3-Flash vs Inkling](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling.md)\n- [GLM-5.3-Flash vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm3-audio-2b.md)\n- [GLM-5.3 vs Inkling](https://www.anchorterminal.com/compare/glm-5-3-vs-inkling.md)\n- [GLM-5.3 vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/glm-5-3-vs-lfm3-audio-2b.md)\n- [gpt-oss-120b vs Inkling](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-inkling.md)\n- [gpt-oss-120b vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-lfm3-audio-2b.md)\n- [gpt-oss-20b vs Inkling](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling.md)\n- [gpt-oss-20b vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm3-audio-2b.md)\n- [Granite 4.2 30B vs Inkling](https://www.anchorterminal.com/compare/granite-4-2-30b-vs-inkling.md)\n- [Granite 4.2 30B vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/granite-4-2-30b-vs-lfm3-audio-2b.md)\n- [Granite 4.2 3B vs Inkling](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-inkling.md)\n- [Granite 4.2 3B vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-lfm3-audio-2b.md)\n- [Granite 4.2 8B vs Inkling](https://www.anchorterminal.com/compare/granite-4-2-8b-vs-inkling.md)\n- [Granite 4.2 8B vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/granite-4-2-8b-vs-lfm3-audio-2b.md)\n- [Hy-Memory-30B-A3B vs Inkling](https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-inkling.md)\n- [Hy-Memory-30B-A3B vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-lfm3-audio-2b.md)\n- [Hy3 vs Inkling](https://www.anchorterminal.com/compare/hy3-vs-inkling.md)\n- [Hy3 vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/hy3-vs-lfm3-audio-2b.md)\n- [Inkling-Small vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/inkling-small-vs-lfm3-audio-2b.md)\n- [Inkling vs Inkling-Small](https://www.anchorterminal.com/compare/inkling-vs-inkling-small.md)\n- [Inkling vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/inkling-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)\n- [Inkling vs Kimi K3](https://www.anchorterminal.com/compare/inkling-vs-kimi-k3.md)\n- [Inkling vs Kimi K3.1 Pro](https://www.anchorterminal.com/compare/inkling-vs-kimi-k3-1-pro.md)\n- [Inkling vs Kolibri-1](https://www.anchorterminal.com/compare/inkling-vs-kolibri-1.md)\n- [Inkling vs Kronos](https://www.anchorterminal.com/compare/inkling-vs-kronos.md)\n- [Inkling vs Laguna M.1](https://www.anchorterminal.com/compare/inkling-vs-laguna-m-1.md)\n- [Inkling vs Laguna S 2.1](https://www.anchorterminal.com/compare/inkling-vs-laguna-s-2-1.md)\n- [Inkling vs Laguna XS 2.1](https://www.anchorterminal.com/compare/inkling-vs-laguna-xs-2-1.md)\n- [Inkling vs LBS-27B](https://www.anchorterminal.com/compare/inkling-vs-lbs-27b.md)\n- [Inkling vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/inkling-vs-lfm2-5-2-6b.md)\n- [Inkling vs LFM3-1.7B](https://www.anchorterminal.com/compare/inkling-vs-lfm3-1-7b.md)\n- [Inkling vs LFM3-Omni-2B](https://www.anchorterminal.com/compare/inkling-vs-lfm3-omni-2b.md)\n- [Inkling vs LFM3-VL-2B](https://www.anchorterminal.com/compare/inkling-vs-lfm3-vl-2b.md)\n- [Inkling vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/inkling-vs-ling-3-0-tiny.md)\n- [Inkling vs Ling-3.1-flash-1019](https://www.anchorterminal.com/compare/inkling-vs-ling-3-1-flash-1019.md)\n- [Inkling vs LongCat-2.5](https://www.anchorterminal.com/compare/inkling-vs-longcat-2-5.md)\n- [Inkling vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/inkling-vs-mimo-v2-6-distill-qwen-9b.md)\n- [Inkling vs MiMo-V2.6-Flash-RL](https://www.anchorterminal.com/compare/inkling-vs-mimo-v2-6-flash-rl.md)\n- [Inkling vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/inkling-vs-minicpm-o-4-5.md)\n- [Inkling vs MiniCPM-V 4.7 1B](https://www.anchorterminal.com/compare/inkling-vs-minicpm-v-4-7-1b.md)\n- [Inkling vs MiniCPM-V 4.7 35B-A3B](https://www.anchorterminal.com/compare/inkling-vs-minicpm-v-4-7-35b-a3b.md)\n- [Inkling vs MiniCPM5-2B](https://www.anchorterminal.com/compare/inkling-vs-minicpm5-2b.md)\n- [Inkling vs MiniMax-M2.5](https://www.anchorterminal.com/compare/inkling-vs-minimax-m2-5.md)\n- [Inkling vs MiniMax-M2.7](https://www.anchorterminal.com/compare/inkling-vs-minimax-m2-7.md)\n- [Inkling vs MiniMax-M3.1-Flash](https://www.anchorterminal.com/compare/inkling-vs-minimax-m3-1-flash.md)\n- [Inkling vs Mistral Large 4](https://www.anchorterminal.com/compare/inkling-vs-mistral-large-4.md)\n- [Inkling vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/inkling-vs-muse-glimmer-30b.md)\n- [Inkling vs Nanbeige4.2-3B](https://www.anchorterminal.com/compare/inkling-vs-nanbeige-4-2-3b.md)\n- [Inkling vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/inkling-vs-nanbeige-4-3-33b.md)\n- [Inkling vs NVIDIA Nemotron 3.5 Bolt E4B 4GB](https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-5-bolt-e4b-4gb.md)\n- [Inkling vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [Inkling vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-nano-30b-a3b.md)\n- [Inkling vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-nano-4b.md)\n- [Inkling vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [Inkling vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-super-120b-a12b.md)\n- [Inkling vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-ultra-550b-a55b.md)\n- [Inkling vs North Mini Code 1.0](https://www.anchorterminal.com/compare/inkling-vs-north-mini-code-1-0.md)\n- [Inkling vs occamy-1.0](https://www.anchorterminal.com/compare/inkling-vs-occamy-1-0.md)\n- [Inkling vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/inkling-vs-olmo-3-7b-think.md)\n- [Inkling vs Ornith-1.5-122B](https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-122b.md)\n- [Inkling vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-35b-a3b.md)\n- [Inkling vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-397b.md)\n- [Inkling vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-9b.md)\n- [Inkling vs OTel-2.0-LLM-31B-IT](https://www.anchorterminal.com/compare/inkling-vs-otel-2-0-llm-31b-it.md)\n- [Inkling vs Qwen-AgentWorld-35B-A3B](https://www.anchorterminal.com/compare/inkling-vs-qwen-agentworld-35b-a3b.md)\n- [Inkling vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/inkling-vs-qwen3-30b-a3b-instruct-2507.md)\n- [Inkling vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/inkling-vs-qwen3-4b-instruct-2507.md)\n- [Inkling vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-0-8b.md)\n- [Inkling vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-122b-a10b.md)\n- [Inkling vs Qwen3.5-2B](https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-2b.md)\n- [Inkling vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-397b-a17b.md)\n- [Inkling vs Qwen3.5-4B](https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-4b.md)\n- [Inkling vs Qwen3.5-9B](https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-9b.md)\n- [Inkling vs Qwen3.6-27B](https://www.anchorterminal.com/compare/inkling-vs-qwen3-6-27b.md)\n- [Inkling vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/inkling-vs-qwen3-6-35b-a3b.md)\n- [Inkling vs Qwen3.8-27B](https://www.anchorterminal.com/compare/inkling-vs-qwen3-8-27b.md)\n- [Inkling vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/inkling-vs-qwen3-8-flash-next.md)\n- [Inkling vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/inkling-vs-qwen3-coder-30b-a3b-instruct.md)\n- [Inkling vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/inkling-vs-qwen3-coder-next.md)\n- [Inkling vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/inkling-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Inkling vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-2b-instruct.md)\n- [Inkling vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-30b-a3b-instruct.md)\n- [Inkling vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-32b-instruct.md)\n- [Inkling vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-4b-instruct.md)\n- [Inkling vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-8b-instruct.md)\n- [Inkling vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/inkling-vs-qwopus3-8-27b-flash-v2.md)\n- [Inkling vs Recursive Flint](https://www.anchorterminal.com/compare/inkling-vs-recursive-flint.md)\n- [Inkling vs Ripple-65B Preview](https://www.anchorterminal.com/compare/inkling-vs-ripple-65b-preview.md)\n- [Inkling vs SenseNova-Loop-9B-Preview](https://www.anchorterminal.com/compare/inkling-vs-sensenova-loop-9b-preview.md)\n- [Inkling vs SmolLM3-3B](https://www.anchorterminal.com/compare/inkling-vs-smollm3-3b.md)\n- [Inkling vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/inkling-vs-spark-x2-6-4b.md)\n- [Inkling vs Step 3.7 Flash](https://www.anchorterminal.com/compare/inkling-vs-step-3-7-flash.md)\n- [Inkling vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/inkling-vs-swift-1-5-qwen3-8-27b.md)\n- [Inkling vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/inkling-vs-swift-1-5-qwen3-8-flash-next.md)\n- [Inkling vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/inkling-vs-thinkingcap-qwen3-8-27b.md)\n- [Inkling vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/inkling-vs-unlimited-ocr-2.md)\n- [Inkling vs WeVisOne-VL-2B](https://www.anchorterminal.com/compare/inkling-vs-wevisone-vl-2b.md)\n- [Inkling vs WeVisOne-VL-4B](https://www.anchorterminal.com/compare/inkling-vs-wevisone-vl-4b.md)\n- [Inkling vs ZAYA1-8B](https://www.anchorterminal.com/compare/inkling-vs-zaya1-8b.md)\n- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-lfm3-audio-2b.md)\n- [Kimi K3.1 Pro vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/kimi-k3-1-pro-vs-lfm3-audio-2b.md)\n- [Kimi K3 vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/kimi-k3-vs-lfm3-audio-2b.md)\n- [Kolibri-1 vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/kolibri-1-vs-lfm3-audio-2b.md)\n- [Kronos vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/kronos-vs-lfm3-audio-2b.md)\n- [Laguna M.1 vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/laguna-m-1-vs-lfm3-audio-2b.md)\n- [Laguna S 2.1 vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/laguna-s-2-1-vs-lfm3-audio-2b.md)\n- [Laguna XS 2.1 vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-lfm3-audio-2b.md)\n- [LBS-27B vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/lbs-27b-vs-lfm3-audio-2b.md)\n- [LFM2.5-2.6B vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-lfm3-audio-2b.md)\n- [LFM3-1.7B vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-lfm3-audio-2b.md)\n- [LFM3-Audio-2B vs LFM3-Omni-2B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-lfm3-omni-2b.md)\n- [LFM3-Audio-2B vs LFM3-VL-2B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-lfm3-vl-2b.md)\n- [LFM3-Audio-2B vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ling-3-0-tiny.md)\n- [LFM3-Audio-2B vs Ling-3.1-flash-1019](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ling-3-1-flash-1019.md)\n- [LFM3-Audio-2B vs LongCat-2.5](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-longcat-2-5.md)\n- [LFM3-Audio-2B vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-mimo-v2-6-distill-qwen-9b.md)\n- [LFM3-Audio-2B vs MiMo-V2.6-Flash-RL](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-mimo-v2-6-flash-rl.md)\n- [LFM3-Audio-2B vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minicpm-o-4-5.md)\n- [LFM3-Audio-2B vs MiniCPM-V 4.7 1B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minicpm-v-4-7-1b.md)\n- [LFM3-Audio-2B vs MiniCPM-V 4.7 35B-A3B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minicpm-v-4-7-35b-a3b.md)\n- [LFM3-Audio-2B vs MiniCPM5-2B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minicpm5-2b.md)\n- [LFM3-Audio-2B vs MiniMax-M2.5](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minimax-m2-5.md)\n- [LFM3-Audio-2B vs MiniMax-M2.7](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minimax-m2-7.md)\n- [LFM3-Audio-2B vs MiniMax-M3.1-Flash](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-minimax-m3-1-flash.md)\n- [LFM3-Audio-2B vs Mistral Large 4](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-mistral-large-4.md)\n- [LFM3-Audio-2B vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-muse-glimmer-30b.md)\n- [LFM3-Audio-2B vs Nanbeige4.2-3B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nanbeige-4-2-3b.md)\n- [LFM3-Audio-2B vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nanbeige-4-3-33b.md)\n- [LFM3-Audio-2B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-5-bolt-e4b-4gb.md)\n- [LFM3-Audio-2B vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [LFM3-Audio-2B vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-nano-30b-a3b.md)\n- [LFM3-Audio-2B vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-nano-4b.md)\n- [LFM3-Audio-2B vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [LFM3-Audio-2B vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-super-120b-a12b.md)\n- [LFM3-Audio-2B vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-nemotron-3-ultra-550b-a55b.md)\n- [LFM3-Audio-2B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-north-mini-code-1-0.md)\n- [LFM3-Audio-2B vs occamy-1.0](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-occamy-1-0.md)\n- [LFM3-Audio-2B vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-olmo-3-7b-think.md)\n- [LFM3-Audio-2B vs Ornith-1.5-122B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ornith-1-5-122b.md)\n- [LFM3-Audio-2B vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ornith-1-5-35b-a3b.md)\n- [LFM3-Audio-2B vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ornith-1-5-397b.md)\n- [LFM3-Audio-2B vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ornith-1-5-9b.md)\n- [LFM3-Audio-2B vs OTel-2.0-LLM-31B-IT](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-otel-2-0-llm-31b-it.md)\n- [LFM3-Audio-2B vs Qwen-AgentWorld-35B-A3B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen-agentworld-35b-a3b.md)\n- [LFM3-Audio-2B vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-30b-a3b-instruct-2507.md)\n- [LFM3-Audio-2B vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-4b-instruct-2507.md)\n- [LFM3-Audio-2B vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-5-0-8b.md)\n- [LFM3-Audio-2B vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-5-122b-a10b.md)\n- [LFM3-Audio-2B vs Qwen3.5-2B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-5-2b.md)\n- [LFM3-Audio-2B vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-5-397b-a17b.md)\n- [LFM3-Audio-2B vs Qwen3.5-4B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-5-4b.md)\n- [LFM3-Audio-2B vs Qwen3.5-9B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-5-9b.md)\n- [LFM3-Audio-2B vs Qwen3.6-27B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-6-27b.md)\n- [LFM3-Audio-2B vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-6-35b-a3b.md)\n- [LFM3-Audio-2B vs Qwen3.8-27B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-8-27b.md)\n- [LFM3-Audio-2B vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-8-flash-next.md)\n- [LFM3-Audio-2B vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-coder-30b-a3b-instruct.md)\n- [LFM3-Audio-2B vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-coder-next.md)\n- [LFM3-Audio-2B vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-omni-30b-a3b-instruct.md)\n- [LFM3-Audio-2B vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-vl-2b-instruct.md)\n- [LFM3-Audio-2B vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-vl-30b-a3b-instruct.md)\n- [LFM3-Audio-2B vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-vl-32b-instruct.md)\n- [LFM3-Audio-2B vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-vl-4b-instruct.md)\n- [LFM3-Audio-2B vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwen3-vl-8b-instruct.md)\n- [LFM3-Audio-2B vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-qwopus3-8-27b-flash-v2.md)\n- [LFM3-Audio-2B vs Recursive Flint](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-recursive-flint.md)\n- [LFM3-Audio-2B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-ripple-65b-preview.md)\n- [LFM3-Audio-2B vs SenseNova-Loop-9B-Preview](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-sensenova-loop-9b-preview.md)\n- [LFM3-Audio-2B vs SmolLM3-3B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-smollm3-3b.md)\n- [LFM3-Audio-2B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-spark-x2-6-4b.md)\n- [LFM3-Audio-2B vs Step 3.7 Flash](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-step-3-7-flash.md)\n- [LFM3-Audio-2B vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-swift-1-5-qwen3-8-27b.md)\n- [LFM3-Audio-2B vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-swift-1-5-qwen3-8-flash-next.md)\n- [LFM3-Audio-2B vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-thinkingcap-qwen3-8-27b.md)\n- [LFM3-Audio-2B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-unlimited-ocr-2.md)\n- [LFM3-Audio-2B vs WeVisOne-VL-2B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-wevisone-vl-2b.md)\n- [LFM3-Audio-2B vs WeVisOne-VL-4B](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-wevisone-vl-4b.md)\n- [LFM3-Audio-2B vs ZAYA1-8B](https://www.anchorterminal.com/compare/lfm3-audio-2b-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": "2026-11-10", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "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 vs LFM3-Audio-2B", "url": "" } ], "description": "Inkling scores 64.7 (B) to LFM3-Audio-2B's 61 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Inkling B 64.7", "LFM3-Audio-2B C 61", "scores" ], "h1": "Inkling vs LFM3-Audio-2B", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/inkling-vs-lfm3-audio-2b", "published": "2026-10-01", "section": "tools", "title": "Inkling vs LFM3-Audio-2B for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-10", "url": "https://www.anchorterminal.com/compare/inkling-vs-lfm3-audio-2b" }, "tokens": { "markdown": 8850, "slim": 680 }, "version": 1 }