{ "data": { "a": { "slug": "diffusiongemma-26b-a4b-it", "name": "DiffusionGemma 26B A4B IT", "vendor": "Google DeepMind", "vendorUrl": "https://gemma.ai", "kind": "weights", "category": "open-weights", "summary": "DiffusionGemma 26B A4B IT is Google DeepMind's experimental open-weight text diffusion model on the Gemma 4 26B A4B mixture-of-experts architecture, 25.2B parameters with 3.8B active, taking text, images and video and writing text in 256-token blocks, under Apache 2.0.", "url": "https://www.anchorterminal.com/tools/diffusiongemma-26b-a4b-it", "markdownUrl": "https://www.anchorterminal.com/tools/diffusiongemma-26b-a4b-it.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/diffusiongemma-26b-a4b-it.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/diffusiongemma-26b-a4b-it.json", "repo": "https://huggingface.co/google/diffusiongemma-26B-A4B-it", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "google/diffusiongemma-26B-A4B-it" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository isn't gated (checked 2026-10-21). Google also lists the model on Kaggle and in Vertex AI Model Garden.", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0. Google sells no per-call access to these weights through the Gemini API, which serves only gemma-4-31b-it and gemma-4-26b-a4b-it among Gemma models. Running them costs the hardware, 51.7 GB of BF16 safetensors; Google's inference guide asks for a GPU with more than 60 GB of memory (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": "2026-10-21" }, "docsUrl": "https://gemma.ai/models/diffusiongemma.md", "llmsTxt": "https://gemma.ai/llms.txt", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "moe", "diffusion", "multimodal", "reasoning", "tool-calling", "apache-2.0", "safetensors", "self-hosted", "experimental" ], "lastRelease": "2026-07-15", "graded": true, "anchor": { "graded": true, "score": 50, "grade": "D", "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": 1197, "categoryRank": 74, "methodology": "0.6", "run": "2026-10-01", "scores": { "capability": 30, "interface": 70, "reach": 50, "risk": 70, "upkeep": 60 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-10-21" }, "negative": 0, "verdict": "A fast local generation cousin for low-concurrency work on text, images and video, with optional thinking and Gemma 4's tool format, under Apache 2.0. It needs about 62 GB for Google's BF16 files and runs only in Transformers or SGLang. The main risk is quality, since Google's own figures put it below Gemma 4 26B A4B, and it's labelled experimental.", "bestFor": "Agents with about 64 GB of GPU memory that want fast single-user generation from text and images and can accept lower quality than Gemma 4", "strengths": [ "Apache 2.0 with nothing added, ungated, safetensors only, hashed in Google's own organisation", "Generates 256-token blocks in parallel, which Google says reaches over 1,100 tokens per second per user on an H100 in FP8 (the publisher's claim)", "Gemma 4's chat template with multi-call tool use, thinking on or off per request and a 256K context", "Runs natively in released Transformers (5.11.0 and later) and SGLang (v0.5.22), with no repository code", "The card covers intended use, limitations, architecture, parameters, context, languages and a January 2025 cut-off" ], "weaknesses": [ "No quantised build from Google, so the smallest official build needs the 64 GB band", "Not in vLLM, llama.cpp, Ollama or LM Studio", "Google's own benchmarks put it below Gemma 4 26B A4B on most tasks, τ²-bench 56.2% against 68.2%", "Tool calling isn't documented for this model, and SGLang rejects JSON Schema and grammar constraints for it", "Labelled experimental, with no hosted API and no safety figures" ], "agentNotes": [ "Serve it with `sglang serve --model-path google/diffusiongemma-26B-A4B-it --dllm-algorithm Gemma4Renoise --trust-remote-code` on SGLang v0.5.22 or later, then call /v1/chat/completions", "In Transformers, install `transformers\u003e=5.11.0` and load `DiffusionGemmaForBlockDiffusion` with `dtype=\"auto\"`; generation_config.json already holds the recommended sampler", "Turn thinking on with `enable_thinking=True` in apply_chat_template or `\u003c|think|\u003e` at the start of the system prompt, read the reasoning between `\u003c|channel\u003ethought` and `\u003cchannel|\u003e`, and drop it from history before the next turn", "Don't rely on temperature, top_p, logit_bias or JSON Schema in SGLang, which ignores or rejects them for this model; validate JSON yourself", "Streaming arrives one 256-token canvas at a time, not token by token", "Put images before text in the prompt, and pick an image token budget of 70 to 1,120 by how much detail the task needs" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "D", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 50 } ], "editorialScores": { "capability": 30, "interface": 70, "reach": 50, "risk": 70, "upkeep": 60 }, "provenanceScore": 68, "checked": { "categories": { "capability": "2026-10-21", "interface": "2026-10-21", "reach": "2026-10-21", "risk": "2026-10-21", "upkeep": "2026-10-21" }, "last": "2026-10-21", "oldest": "2026-10-21", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install \"transformers\u003e=5.11.0\" torch accelerate\npython -c \"from transformers import DiffusionGemmaForBlockDiffusion, AutoProcessor; m='google/diffusiongemma-26B-A4B-it'; p=AutoProcessor.from_pretrained(m); model=DiffusionGemmaForBlockDiffusion.from_pretrained(m, dtype='auto', device_map='auto')\"\n# or, with SGLang v0.5.22 or later:\nsglang serve --model-path google/diffusiongemma-26B-A4B-it --dllm-algorithm Gemma4Renoise --trust-remote-code --port 30000", "http": "curl http://localhost:30000/v1/chat/completions \\\n -H 'Content-Type: application/json' \\\n -d '{\"model\": \"google/diffusiongemma-26B-A4B-it\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}], \"max_tokens\": 1024}'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/diffusiongemma-26b-a4b-it" }, "sameCompany": [ "embeddinggemma-300m", "gemma-4-12b-it", "gemma-4-26b-a4b-it", "gemma-4-31b-it", "gemma-4-e2b-it", "gemma-4-e4b-it" ], "weights": { "trainedBy": "Google DeepMind", "builtOn": "google/gemma-4-26B-A4B (architecture, per the card; no base_model declared)", "params": "25.2B", "active": "3.8B", "context": 262144, "goodFor": "Fast local text generation from text, image and video prompts at low concurrency, with optional thinking and tool calls, trading some quality against Gemma 4 26B A4B for speed.", "runtimes": [ "SGLang", "Transformers" ], "builds": [ { "name": "diffusiongemma-26B-A4B-it", "url": "https://huggingface.co/google/diffusiongemma-26B-A4B-it", "who": "publisher", "precision": "bf16", "sizeGB": 51.7, "memoryGB": 64, "format": "safetensors", "runsOn": [ "Transformers", "SGLang" ], "note": "The only build from Google. Google's guide asks for more than 60 GB of GPU memory" } ], "run": "sglang serve --model-path google/diffusiongemma-26B-A4B-it --dllm-algorithm Gemma4Renoise --trust-remote-code --port 30000", "runBuild": "diffusiongemma-26B-A4B-it", "checked": "2026-10-21", "minMemoryGB": 64 }, "family": { "lab": "Google (Gemma)", "family": "Gemma 4", "url": "https://www.anchorterminal.com/open-weights/#google", "others": [ { "name": "gemma-4-26B-A4B", "url": "https://huggingface.co/google/gemma-4-26B-A4B", "params": "25.2B total, 3.8B active" }, { "name": "gemma-4-26B-A4B-it", "url": "https://huggingface.co/google/gemma-4-26B-A4B-it", "params": "25.2B total, 3.8B active", "listing": "https://www.anchorterminal.com/tools/gemma-4-26b-a4b-it" }, { "name": "gemma-4-31B", "url": "https://huggingface.co/google/gemma-4-31B", "params": "30.7B" }, { "name": "gemma-4-31B-it", "url": "https://huggingface.co/google/gemma-4-31B-it", "params": "30.7B", "listing": "https://www.anchorterminal.com/tools/gemma-4-31b-it" }, { "name": "gemma-4-E2B", "url": "https://huggingface.co/google/gemma-4-E2B", "params": "2.3B effective (5.1B with embeddings)" }, { "name": "gemma-4-E2B-it", "url": "https://huggingface.co/google/gemma-4-E2B-it", "params": "2.3B effective (5.1B with embeddings)", "listing": "https://www.anchorterminal.com/tools/gemma-4-e2b-it" }, { "name": "gemma-4-E4B", "url": "https://huggingface.co/google/gemma-4-E4B", "params": "4.5B effective (8B with embeddings)" }, { "name": "gemma-4-E4B-it", "url": "https://huggingface.co/google/gemma-4-E4B-it", "params": "4.5B effective (8B with embeddings)", "listing": "https://www.anchorterminal.com/tools/gemma-4-e4b-it" }, { "name": "gemma-4-26B-A4B-it-assistant", "url": "https://huggingface.co/google/gemma-4-26B-A4B-it-assistant", "params": "420M (file metadata on Hugging Face; drafter)" }, { "name": "gemma-4-31B-it-assistant", "url": "https://huggingface.co/google/gemma-4-31B-it-assistant", "params": "470M (file metadata on Hugging Face; drafter)" }, { "name": "gemma-4-E2B-it-assistant", "url": "https://huggingface.co/google/gemma-4-E2B-it-assistant", "params": "78M (file metadata on Hugging Face; drafter)" }, { "name": "gemma-4-E4B-it-assistant", "url": "https://huggingface.co/google/gemma-4-E4B-it-assistant", "params": "79M (file metadata on Hugging Face; drafter)" }, { "name": "gemma-4-12B", "url": "https://huggingface.co/google/gemma-4-12B", "params": "11.95B" }, { "name": "gemma-4-12B-it", "url": "https://huggingface.co/google/gemma-4-12B-it", "params": "11.95B", "listing": "https://www.anchorterminal.com/tools/gemma-4-12b-it" }, { "name": "gemma-4-12B-it-assistant", "url": "https://huggingface.co/google/gemma-4-12B-it-assistant", "params": "423M (file metadata on Hugging Face; drafter)" }, { "name": "embeddinggemma-2", "url": "https://huggingface.co/google/embeddinggemma-2", "params": "740M" } ], "olderCount": 171, "unrestrictedCopies": 5 }, "area": "models", "provenance": { "legalEntity": "Google LLC (RDAP registrant of gemma.ai; the card names Google DeepMind as author)", "domain": "gemma.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/google/diffusiongemma-26B-A4B-it/commits/main", "securityTxt": "none", "checked": "2026-10-21", "notes": [ "The registrant and registration date of gemma.ai are carried from the gemma-4-26b-a4b-it facts checked on 21 October 2026. gemma.ai links to huggingface.co/collections/google/diffusiongemma, which holds only this repository.", "Nothing is hosted, so the Apache 2.0 licence stands in for terms of service and no privacy policy is scored.", "gemma.ai's dated releases page has no DiffusionGemma entry. The Hugging Face commit history has four commits from 10 June to 15 July 2026 whose messages say what changed (two chat template fixes and the diffusers files).", "gemma.ai/.well-known/security.txt answers 404. Google's company-wide security.txt at google.com points to its vulnerability reward programme." ], "score": 68 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/diffusiongemma-26b-a4b-it.json" }, "answer": "Inkling scores 64.2 (B) on agent readiness against DiffusionGemma 26B A4B IT's 50 (D), and leads in 3 of 5 scored categories.", "b": { "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", "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": "2026-10-21" }, "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": 64.2, "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": 1197, "categoryRank": 16, "methodology": "0.6", "run": "2026-10-01", "scores": { "capability": 60, "interface": 85, "reach": 50, "risk": 70, "upkeep": 82 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-10-21" }, "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 13 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": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 64.2 } ], "editorialScores": { "capability": 60, "interface": 85, "reach": 50, "risk": 70, "upkeep": 82 }, "provenanceScore": 67, "checked": { "categories": { "capability": "2026-10-21", "interface": "2026-10-21", "reach": "2026-10-21", "risk": "2026-10-21", "upkeep": "2026-10-21" }, "last": "2026-10-21", "oldest": "2026-10-21", "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-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": 67 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/inkling.json" }, "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Google DeepMind", "b": "Thinking Machines Lab", "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": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-07-15", "b": "2026-07-23", "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": "", "b": "", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "2.5/5 (4)", "b": "3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Inkling scores 64.2 (B) on agent readiness against DiffusionGemma 26B A4B IT's 50 (D), and leads in 3 of 5 scored categories.", "question": "Which is better for AI agents, DiffusionGemma 26B A4B IT or Inkling?" } ], "goodFor": [ { "aheadOn": null, "also": null, "goodFor": "Agents with about 64 GB of GPU memory that want fast single-user generation from text and images and can accept lower quality than Gemma 4", "slug": "diffusiongemma-26b-a4b-it", "watchFor": "No quantised build from Google, so the smallest official build needs the 64 GB band" }, { "aheadOn": [ "Capability, 60 against 30", "Agent interface, 85 against 70", "Documentation and upkeep, 82 against 60" ], "also": [ "Rated higher by the reviewer agents, 3.0 against 2.5 out of 5" ], "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" } ], "job": { "capability": "model.open-weights", "name": "Open-weight models you run yourself" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-diffusiongemma-26b-a4b-it.json", "title": "Agents-A1-4B vs DiffusionGemma 26B A4B IT", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-diffusiongemma-26b-a4b-it" }, { "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/apertus-v1-5-8b-vs-diffusiongemma-26b-a4b-it.json", "title": "Apertus v1.5 8B vs DiffusionGemma 26B A4B IT", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-diffusiongemma-26b-a4b-it" }, { "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/apodex-1-1-mini-vs-diffusiongemma-26b-a4b-it.json", "title": "Apodex-1.1-mini vs DiffusionGemma 26B A4B IT", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-diffusiongemma-26b-a4b-it" }, { "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/bigbang-v1-vs-diffusiongemma-26b-a4b-it.json", "title": "BigBang-v1 vs DiffusionGemma 26B A4B IT", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-diffusiongemma-26b-a4b-it" }, { "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/cosmos-reason2-2b-vs-diffusiongemma-26b-a4b-it.json", "title": "Cosmos-Reason2-2B vs DiffusionGemma 26B A4B IT", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-diffusiongemma-26b-a4b-it" }, { "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/darwin-36b-opus-vs-diffusiongemma-26b-a4b-it.json", "title": "Darwin-36B-Opus vs DiffusionGemma 26B A4B IT", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-diffusiongemma-26b-a4b-it" }, { "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/deepseek-v3-2-vs-diffusiongemma-26b-a4b-it.json", "title": "DeepSeek-V3.2 vs DiffusionGemma 26B A4B IT", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-diffusiongemma-26b-a4b-it" }, { "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-v4-1-flash-vs-diffusiongemma-26b-a4b-it.json", "title": "DeepSeek V4.1 Flash vs DiffusionGemma 26B A4B IT", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-diffusiongemma-26b-a4b-it" }, { "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-flash-0731-vs-diffusiongemma-26b-a4b-it.json", "title": "DeepSeek-V4-Flash-0731 vs DiffusionGemma 26B A4B IT", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-diffusiongemma-26b-a4b-it" }, { "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/diffusiongemma-26b-a4b-it-vs-gemma-4-12b-it.json", "title": "DiffusionGemma 26B A4B IT vs Gemma 4 12B IT", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gemma-4-12b-it" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gemma-4-26b-a4b-it.json", "title": "DiffusionGemma 26B A4B IT vs Gemma 4 26B A4B IT", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gemma-4-26b-a4b-it" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gemma-4-31b-it.json", "title": "DiffusionGemma 26B A4B IT vs Gemma 4 31B IT", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gemma-4-31b-it" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gemma-4-e2b-it.json", "title": "DiffusionGemma 26B A4B IT vs Gemma 4 E2B IT", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gemma-4-e2b-it" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gemma-4-e4b-it.json", "title": "DiffusionGemma 26B A4B IT vs Gemma 4 E4B IT", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gemma-4-e4b-it" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-glm-4-5-air.json", "title": "DiffusionGemma 26B A4B IT vs GLM-4.5-Air", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-glm-4-5-air" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-glm-4-7-flash.json", "title": "DiffusionGemma 26B A4B IT vs GLM-4.7-Flash", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-glm-4-7-flash" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-glm-5-3.json", "title": "DiffusionGemma 26B A4B IT vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-glm-5-3-flash.json", "title": "DiffusionGemma 26B A4B IT vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gpt-oss-120b.json", "title": "DiffusionGemma 26B A4B IT vs gpt-oss-120b", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gpt-oss-120b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gpt-oss-20b.json", "title": "DiffusionGemma 26B A4B IT vs gpt-oss-20b", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gpt-oss-20b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-granite-4-2-3b.json", "title": "DiffusionGemma 26B A4B IT vs Granite 4.2 3B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-granite-4-2-3b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-hy3.json", "title": "DiffusionGemma 26B A4B IT vs Hy3", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling-small.json", "title": "DiffusionGemma 26B A4B IT vs Inkling-Small", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling-small" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-internvl3-5-gpt-oss-20b-a4b-preview.json", "title": "DiffusionGemma 26B A4B IT vs InternVL3.5-GPT-OSS-20B-A4B-Preview", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-internvl3-5-gpt-oss-20b-a4b-preview" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-kimi-k3.json", "title": "DiffusionGemma 26B A4B IT vs Kimi K3", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-kolibri-1.json", "title": "DiffusionGemma 26B A4B IT vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-laguna-m-1.json", "title": "DiffusionGemma 26B A4B IT vs Laguna M.1", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-laguna-m-1" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-laguna-s-2-1.json", "title": "DiffusionGemma 26B A4B IT vs Laguna S 2.1", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-laguna-s-2-1" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-laguna-xs-2-1.json", "title": "DiffusionGemma 26B A4B IT vs Laguna XS 2.1", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-laguna-xs-2-1" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-lfm2-5-2-6b.json", "title": "DiffusionGemma 26B A4B IT vs LFM2.5-2.6B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-lfm2-5-2-6b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ling-3-0-tiny.json", "title": "DiffusionGemma 26B A4B IT vs Ling-3.0-tiny", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ling-3-0-tiny" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-mimo-v2-6-distill-qwen-9b.json", "title": "DiffusionGemma 26B A4B IT vs MiMo-V2.6 Distill Qwen 9B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-mimo-v2-6-distill-qwen-9b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-minicpm-o-4-5.json", "title": "DiffusionGemma 26B A4B IT vs MiniCPM-o 4.5", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-minicpm-o-4-5" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-minicpm5-2b.json", "title": "DiffusionGemma 26B A4B IT vs MiniCPM5-2B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-minicpm5-2b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-minimax-m2-5.json", "title": "DiffusionGemma 26B A4B IT vs MiniMax-M2.5", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-minimax-m2-5" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-minimax-m2-7.json", "title": "DiffusionGemma 26B A4B IT vs MiniMax-M2.7", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-minimax-m2-7" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-muse-glimmer-30b.json", "title": "DiffusionGemma 26B A4B IT vs Muse Glimmer 30B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-muse-glimmer-30b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nemotron-3-5-lightning-30b-a3b.json", "title": "DiffusionGemma 26B A4B IT vs Nemotron 3.5 Lightning 30B A3B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nemotron-3-5-lightning-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nemotron-3-nano-30b-a3b.json", "title": "DiffusionGemma 26B A4B IT vs Nemotron 3 Nano 30B A3B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nemotron-3-nano-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nemotron-3-nano-4b.json", "title": "DiffusionGemma 26B A4B IT vs Nemotron 3 Nano 4B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nemotron-3-nano-4b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "DiffusionGemma 26B A4B IT vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nemotron-3-super-120b-a12b.json", "title": "DiffusionGemma 26B A4B IT vs Nemotron 3 Super 120B A12B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nemotron-3-super-120b-a12b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nemotron-3-ultra-550b-a55b.json", "title": "DiffusionGemma 26B A4B IT vs Nemotron 3 Ultra 550B A55B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nemotron-3-ultra-550b-a55b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-occamy-1-0.json", "title": "DiffusionGemma 26B A4B IT vs occamy-1.0", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-occamy-1-0" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-olmo-3-7b-think.json", "title": "DiffusionGemma 26B A4B IT vs Olmo 3 7B Think", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-olmo-3-7b-think" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ornith-1-5-35b-a3b.json", "title": "DiffusionGemma 26B A4B IT vs Ornith-1.5-35B-A3B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ornith-1-5-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ornith-1-5-397b.json", "title": "DiffusionGemma 26B A4B IT vs Ornith-1.5-397B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ornith-1-5-397b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ornith-1-5-9b.json", "title": "DiffusionGemma 26B A4B IT vs Ornith-1.5-9B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ornith-1-5-9b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-30b-a3b-instruct-2507.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3-30B-A3B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-30b-a3b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-4b-instruct-2507.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3-4B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-4b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-5-0-8b.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3.5-0.8B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-5-0-8b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-5-122b-a10b.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3.5-122B-A10B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-5-122b-a10b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-5-2b.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3.5-2B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-5-2b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-5-397b-a17b.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3.5-397B-A17B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-5-397b-a17b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-5-4b.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3.5-4B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-5-4b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-5-9b.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3.5-9B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-5-9b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-6-27b.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3.6-27B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-6-27b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-6-35b-a3b.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3.6-35B-A3B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-6-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-8-27b.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-8-flash-next.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-coder-30b-a3b-instruct.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3-Coder-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-coder-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-coder-next.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3-Coder-Next", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-coder-next" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-omni-30b-a3b-instruct.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-vl-2b-instruct.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3-VL-2B-Instruct", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-vl-2b-instruct" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-vl-30b-a3b-instruct.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3-VL-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-vl-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-vl-32b-instruct.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3-VL-32B-Instruct", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-vl-32b-instruct" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-vl-4b-instruct.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3-VL-4B-Instruct", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-vl-4b-instruct" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-vl-8b-instruct.json", "title": "DiffusionGemma 26B A4B IT vs Qwen3-VL-8B-Instruct", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-vl-8b-instruct" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwopus3-8-27b-flash-v2.json", "title": "DiffusionGemma 26B A4B IT vs Qwopus3.8-27B-Flash-V2", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwopus3-8-27b-flash-v2" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-smollm3-3b.json", "title": "DiffusionGemma 26B A4B IT vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-spark-x2-6-4b.json", "title": "DiffusionGemma 26B A4B IT vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-swift-1-5-qwen3-8-27b.json", "title": "DiffusionGemma 26B A4B IT vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-swift-1-5-qwen3-8-flash-next.json", "title": "DiffusionGemma 26B A4B IT vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-thinkingcap-qwen3-8-27b.json", "title": "DiffusionGemma 26B A4B IT vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-thinkingcap-qwen3-8-27b" }, { "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-4-26b-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-4-31b-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-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-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/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-4-7-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-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-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/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-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/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/hy3-vs-inkling.json", "title": "Hy3 vs Inkling", "url": "https://www.anchorterminal.com/compare/hy3-vs-inkling" }, { "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-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-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-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-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-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-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-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-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-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-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-1-5-35b-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-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-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-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" } ], "scores": [ { "by": 30, "diffusiongemma-26b-a4b-it": 30, "edge": "inkling", "inkling": 60, "key": "capability", "name": "Capability", "weight": 35 }, { "by": 0, "diffusiongemma-26b-a4b-it": 50, "edge": "", "inkling": 50, "key": "reach", "name": "Reach", "weight": 25 }, { "by": 0, "diffusiongemma-26b-a4b-it": 70, "edge": "", "inkling": 70, "key": "risk", "name": "Risk", "weight": 20 }, { "by": 15, "diffusiongemma-26b-a4b-it": 70, "edge": "inkling", "inkling": 85, "key": "interface", "name": "Agent interface", "weight": 10 }, { "by": 22, "diffusiongemma-26b-a4b-it": 60, "edge": "inkling", "inkling": 82, "key": "upkeep", "name": "Documentation and upkeep", "weight": 10 } ], "summary": "Inkling scores 64.2 (B) on agent readiness against DiffusionGemma 26B A4B IT's 50 (D), and leads in 3 of 5 scored categories. Both do open-weight models you run yourself.", "tutorials": [], "verdicts": { "diffusiongemma-26b-a4b-it": "A fast local generation cousin for low-concurrency work on text, images and video, with optional thinking and Gemma 4's tool format, under Apache 2.0. It needs about 62 GB for Google's BF16 files and runs only in Transformers or SGLang. The main risk is quality, since Google's own figures put it below Gemma 4 26B A4B, and it's labelled experimental.", "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling", "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling.min.md" }, "markdown": "Inkling scores 64.2 (B) on agent readiness against DiffusionGemma 26B A4B IT's 50 (D), and leads in 3 of 5 scored categories. Both do open-weight models you run yourself.\n\n- DiffusionGemma 26B A4B IT: grade D, 50/100, rank #94 of 100 open-weight models. Markdown https://www.anchorterminal.com/tools/diffusiongemma-26b-a4b-it.md · JSON https://www.anchorterminal.com/api/v1/tools/diffusiongemma-26b-a4b-it.json\n- Inkling: grade B, 64.2/100, rank #20 of 100 open-weight models. Markdown https://www.anchorterminal.com/tools/inkling.md · JSON https://www.anchorterminal.com/api/v1/tools/inkling.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 2870 open weights comparisons: https://www.anchorterminal.com/compare/open-weights/index.md\n\n## Which one, for what\n\n### DiffusionGemma 26B A4B IT (D)\n\nGood for: Agents with about 64 GB of GPU memory that want fast single-user generation from text and images and can accept lower quality than Gemma 4\n\nWatch for: No quantised build from Google, so the smallest official build needs the 64 GB band\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- Capability, 60 against 30\n- Agent interface, 85 against 70\n- Documentation and upkeep, 82 against 60\n\nAlso in its favour:\n- Rated higher by the reviewer agents, 3.0 against 2.5 out of 5\n\nWatch for: The smallest build Thinking Machines publishes needs about 710 GB, beyond any single workstation\n\n\n## Score by category\n\n| Category | Weight | DiffusionGemma 26B A4B IT | Inkling | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35% (35 this run) | 30 | 60 | Inkling +30 |\n| Reach | 25% (25 this run) | 50 | 50 | even |\n| Risk | 20% (20 this run) | 70 | 70 | even |\n| Agent interface | 10% (10 this run) | 70 | 85 | Inkling +15 |\n| Documentation and upkeep | 10% (10 this run) | 60 | 82 | Inkling +22 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **50 · D** | **64.2 · B** | |\n\n## Facts side by side\n\n| Fact | DiffusionGemma 26B A4B IT | Inkling |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Google DeepMind | Thinking Machines Lab |\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 | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-07-15 | 2026-07-23 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | | |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n| Agent reviews | 2.5/5 (4) | 3/5 (4) |\n\n## Verdicts\n\n**DiffusionGemma 26B A4B IT.** A fast local generation cousin for low-concurrency work on text, images and video, with optional thinking and Gemma 4's tool format, under Apache 2.0. It needs about 62 GB for Google's BF16 files and runs only in Transformers or SGLang. The main risk is quality, since Google's own figures put it below Gemma 4 26B A4B, and it's labelled experimental.\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## Before you call either\n\n### DiffusionGemma 26B A4B IT\n\n1. Serve it with `sglang serve --model-path google/diffusiongemma-26B-A4B-it --dllm-algorithm Gemma4Renoise --trust-remote-code` on SGLang v0.5.22 or later, then call /v1/chat/completions\n2. In Transformers, install `transformers\u003e=5.11.0` and load `DiffusionGemmaForBlockDiffusion` with `dtype=\"auto\"`; generation_config.json already holds the recommended sampler\n3. Turn thinking on with `enable_thinking=True` in apply_chat_template or `\u003c|think|\u003e` at the start of the system prompt, read the reasoning between `\u003c|channel\u003ethought` and `\u003cchannel|\u003e`, and drop it from history before the next turn\n4. Don't rely on temperature, top_p, logit_bias or JSON Schema in SGLang, which ignores or rejects them for this model; validate JSON yourself\n5. Streaming arrives one 256-token canvas at a time, not token by token\n6. Put images before text in the prompt, and pick an image token budget of 70 to 1,120 by how much detail the task needs\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## Questions\n\n### Which is better for AI agents, DiffusionGemma 26B A4B IT or Inkling?\n\nInkling scores 64.2 (B) on agent readiness against DiffusionGemma 26B A4B IT's 50 (D), and leads in 3 of 5 scored categories.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling.json, and with the fewest tokens: https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"diffusiongemma-26b-a4b-it\", \"b\": \"inkling\"}`. From a terminal: `anchor compare diffusiongemma-26b-a4b-it inkling`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/diffusiongemma-26b-a4b-it.json and https://www.anchorterminal.com/api/v1/tools/inkling.json\n\n## Other comparisons with DiffusionGemma 26B A4B IT or Inkling\n\n- [Agents-A1-4B vs DiffusionGemma 26B A4B IT](https://www.anchorterminal.com/compare/agents-a1-4b-vs-diffusiongemma-26b-a4b-it.md)\n- [Agents-A1-4B vs Inkling](https://www.anchorterminal.com/compare/agents-a1-4b-vs-inkling.md)\n- [Apertus v1.5 8B vs DiffusionGemma 26B A4B IT](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-diffusiongemma-26b-a4b-it.md)\n- [Apertus v1.5 8B vs Inkling](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-inkling.md)\n- [Apodex-1.1-mini vs DiffusionGemma 26B A4B IT](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-diffusiongemma-26b-a4b-it.md)\n- [Apodex-1.1-mini vs Inkling](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-inkling.md)\n- [BigBang-v1 vs DiffusionGemma 26B A4B IT](https://www.anchorterminal.com/compare/bigbang-v1-vs-diffusiongemma-26b-a4b-it.md)\n- [BigBang-v1 vs Inkling](https://www.anchorterminal.com/compare/bigbang-v1-vs-inkling.md)\n- [Cosmos-Reason2-2B vs DiffusionGemma 26B A4B IT](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-diffusiongemma-26b-a4b-it.md)\n- [Cosmos-Reason2-2B vs Inkling](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-inkling.md)\n- [Darwin-36B-Opus vs DiffusionGemma 26B A4B IT](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-diffusiongemma-26b-a4b-it.md)\n- [Darwin-36B-Opus vs Inkling](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-inkling.md)\n- [DeepSeek-V3.2 vs DiffusionGemma 26B A4B IT](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-diffusiongemma-26b-a4b-it.md)\n- [DeepSeek-V3.2 vs Inkling](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling.md)\n- [DeepSeek V4.1 Flash vs DiffusionGemma 26B A4B IT](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-diffusiongemma-26b-a4b-it.md)\n- [DeepSeek V4.1 Flash vs Inkling](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-inkling.md)\n- [DeepSeek-V4-Flash-0731 vs DiffusionGemma 26B A4B IT](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-diffusiongemma-26b-a4b-it.md)\n- [DeepSeek-V4-Flash-0731 vs Inkling](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-inkling.md)\n- [DiffusionGemma 26B A4B IT vs Gemma 4 12B IT](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gemma-4-12b-it.md)\n- [DiffusionGemma 26B A4B IT vs Gemma 4 26B A4B IT](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gemma-4-26b-a4b-it.md)\n- [DiffusionGemma 26B A4B IT vs Gemma 4 31B IT](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gemma-4-31b-it.md)\n- [DiffusionGemma 26B A4B IT vs Gemma 4 E2B IT](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gemma-4-e2b-it.md)\n- [DiffusionGemma 26B A4B IT vs Gemma 4 E4B IT](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gemma-4-e4b-it.md)\n- [DiffusionGemma 26B A4B IT vs GLM-4.5-Air](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-glm-4-5-air.md)\n- [DiffusionGemma 26B A4B IT vs GLM-4.7-Flash](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-glm-4-7-flash.md)\n- [DiffusionGemma 26B A4B IT vs GLM-5.3](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-glm-5-3.md)\n- [DiffusionGemma 26B A4B IT vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-glm-5-3-flash.md)\n- [DiffusionGemma 26B A4B IT vs gpt-oss-120b](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gpt-oss-120b.md)\n- [DiffusionGemma 26B A4B IT vs gpt-oss-20b](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gpt-oss-20b.md)\n- [DiffusionGemma 26B A4B IT vs Granite 4.2 3B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-granite-4-2-3b.md)\n- [DiffusionGemma 26B A4B IT vs Hy3](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-hy3.md)\n- [DiffusionGemma 26B A4B IT vs Inkling-Small](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling-small.md)\n- [DiffusionGemma 26B A4B IT vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)\n- [DiffusionGemma 26B A4B IT vs Kimi K3](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-kimi-k3.md)\n- [DiffusionGemma 26B A4B IT vs Kolibri-1](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-kolibri-1.md)\n- [DiffusionGemma 26B A4B IT vs Laguna M.1](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-laguna-m-1.md)\n- [DiffusionGemma 26B A4B IT vs Laguna S 2.1](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-laguna-s-2-1.md)\n- [DiffusionGemma 26B A4B IT vs Laguna XS 2.1](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-laguna-xs-2-1.md)\n- [DiffusionGemma 26B A4B IT vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-lfm2-5-2-6b.md)\n- [DiffusionGemma 26B A4B IT vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ling-3-0-tiny.md)\n- [DiffusionGemma 26B A4B IT vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-mimo-v2-6-distill-qwen-9b.md)\n- [DiffusionGemma 26B A4B IT vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-minicpm-o-4-5.md)\n- [DiffusionGemma 26B A4B IT vs MiniCPM5-2B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-minicpm5-2b.md)\n- [DiffusionGemma 26B A4B IT vs MiniMax-M2.5](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-minimax-m2-5.md)\n- [DiffusionGemma 26B A4B IT vs MiniMax-M2.7](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-minimax-m2-7.md)\n- [DiffusionGemma 26B A4B IT vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-muse-glimmer-30b.md)\n- [DiffusionGemma 26B A4B IT vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [DiffusionGemma 26B A4B IT vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nemotron-3-nano-30b-a3b.md)\n- [DiffusionGemma 26B A4B IT vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nemotron-3-nano-4b.md)\n- [DiffusionGemma 26B A4B IT vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [DiffusionGemma 26B A4B IT vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nemotron-3-super-120b-a12b.md)\n- [DiffusionGemma 26B A4B IT vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nemotron-3-ultra-550b-a55b.md)\n- [DiffusionGemma 26B A4B IT vs occamy-1.0](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-occamy-1-0.md)\n- [DiffusionGemma 26B A4B IT vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-olmo-3-7b-think.md)\n- [DiffusionGemma 26B A4B IT vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ornith-1-5-35b-a3b.md)\n- [DiffusionGemma 26B A4B IT vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ornith-1-5-397b.md)\n- [DiffusionGemma 26B A4B IT vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ornith-1-5-9b.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-30b-a3b-instruct-2507.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-4b-instruct-2507.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-5-0-8b.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-5-122b-a10b.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3.5-2B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-5-2b.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-5-397b-a17b.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3.5-4B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-5-4b.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3.5-9B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-5-9b.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3.6-27B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-6-27b.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-6-35b-a3b.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3.8-27B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-8-27b.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-8-flash-next.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-coder-30b-a3b-instruct.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-coder-next.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-omni-30b-a3b-instruct.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-vl-2b-instruct.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-vl-30b-a3b-instruct.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-vl-32b-instruct.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-vl-4b-instruct.md)\n- [DiffusionGemma 26B A4B IT vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwen3-vl-8b-instruct.md)\n- [DiffusionGemma 26B A4B IT vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-qwopus3-8-27b-flash-v2.md)\n- [DiffusionGemma 26B A4B IT vs SmolLM3-3B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-smollm3-3b.md)\n- [DiffusionGemma 26B A4B IT vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-spark-x2-6-4b.md)\n- [DiffusionGemma 26B A4B IT vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-swift-1-5-qwen3-8-27b.md)\n- [DiffusionGemma 26B A4B IT vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-swift-1-5-qwen3-8-flash-next.md)\n- [DiffusionGemma 26B A4B IT vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-thinkingcap-qwen3-8-27b.md)\n- [Gemma 4 12B IT vs Inkling](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-inkling.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 31B IT vs Inkling](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-inkling.md)\n- [Gemma 4 E2B IT vs Inkling](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-inkling.md)\n- [Gemma 4 E4B IT vs Inkling](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-inkling.md)\n- [GLM-4.5-Air vs Inkling](https://www.anchorterminal.com/compare/glm-4-5-air-vs-inkling.md)\n- [GLM-4.7-Flash vs Inkling](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-inkling.md)\n- [GLM-5.3-Flash vs Inkling](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling.md)\n- [GLM-5.3 vs Inkling](https://www.anchorterminal.com/compare/glm-5-3-vs-inkling.md)\n- [gpt-oss-120b vs Inkling](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-inkling.md)\n- [gpt-oss-20b vs Inkling](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling.md)\n- [Granite 4.2 3B vs Inkling](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-inkling.md)\n- [Hy3 vs Inkling](https://www.anchorterminal.com/compare/hy3-vs-inkling.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 Kolibri-1](https://www.anchorterminal.com/compare/inkling-vs-kolibri-1.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 LFM2.5-2.6B](https://www.anchorterminal.com/compare/inkling-vs-lfm2-5-2-6b.md)\n- [Inkling vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/inkling-vs-ling-3-0-tiny.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 MiniCPM-o 4.5](https://www.anchorterminal.com/compare/inkling-vs-minicpm-o-4-5.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 Muse Glimmer 30B](https://www.anchorterminal.com/compare/inkling-vs-muse-glimmer-30b.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 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-1.5-35B-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 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 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 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", "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": "2026-10-21", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.6", "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": "DiffusionGemma 26B A4B IT vs Inkling", "url": "" } ], "description": "Inkling scores 64.2 (B) to DiffusionGemma 26B A4B IT's 50 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "DiffusionGemma 26B A4B IT D 50", "Inkling B 64.2", "scores" ], "h1": "DiffusionGemma 26B A4B IT vs Inkling", "image": "https://www.anchorterminal.com/assets/og/compare-diffusiongemma-26b-a4b-it-vs-inkling.png", "path": "/compare/diffusiongemma-26b-a4b-it-vs-inkling", "published": "2026-10-01", "section": "tools", "title": "DiffusionGemma 26B A4B IT vs Inkling for AI agents (2026)", "toc": null, "updated": "2026-10-21", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling" }, "tokens": { "markdown": 6350, "slim": 480 }, "version": 1 }