{ "data": { "a": { "slug": "gemma-4-12b-it", "name": "Gemma 4 12B IT", "vendor": "Google DeepMind", "vendorUrl": "https://gemma.ai", "kind": "weights", "category": "open-weights", "summary": "Gemma 4 12B IT is Google DeepMind's open-weight instruction-tuned dense model, 11.95B parameters in an encoder-free design, taking text, images, video frames and audio with a 262,144-token context, published on Hugging Face under Apache 2.0.", "url": "https://www.anchorterminal.com/tools/gemma-4-12b-it", "markdownUrl": "https://www.anchorterminal.com/tools/gemma-4-12b-it.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gemma-4-12b-it.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gemma-4-12b-it.json", "repo": "https://huggingface.co/google/gemma-4-12B-it", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "google/gemma-4-12B-it" }, { "registry": "huggingface", "name": "google/gemma-4-12B-it-qat-q4_0-gguf" }, { "registry": "huggingface", "name": "google/gemma-4-12B-it-qat-w4a16-ct" }, { "registry": "ollama", "name": "gemma4:12b" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository and Google's QAT repositories are not gated (checked 2026-10-21).", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0. No hosted version, since the Gemini API serves only the 26B A4B and 31B sizes and Hugging Face lists no inference provider for it. Running it yourself costs the hardware, 26.7 GB at BF16, 13.4 GB at SFP8 and 6.7 GB at Q4_0 to load the weights per Google (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/gemma-4/", "llmsTxt": "https://gemma.ai/llms.txt", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "dense", "multimodal", "audio", "reasoning", "tool-calling", "apache-2.0", "safetensors", "gguf", "qat", "self-hosted" ], "lastRelease": "2026-07-20", "graded": true, "anchor": { "graded": true, "score": 71.3, "grade": "BB", "agentReady": true, "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": 3, "methodology": "0.6", "run": "2026-10-01", "scores": { "capability": 50, "interface": 85, "reach": 95, "risk": 70, "upkeep": 75 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-10-21" }, "negative": 0, "verdict": "A mid-size cousin for agent work with tools, optional thinking and image and audio input, under Apache 2.0. Google's 4-bit build needs under 9 GB with working space, so it runs on a 12 GB GPU or any recent Mac in all the common runtimes. The main risks are no published safety results and no documented JSON output.", "bestFor": "Agents on a 12 GB or larger GPU or Mac that want a permissively licensed tool-calling model with images, audio and long context", "strengths": [ "Plain Apache 2.0, no account or gate, safetensors and GGUF only with a checksum on every file", "Google's own 4-bit QAT GGUF needs about 8.6 GB with working space", "Released support in vLLM, SGLang, llama.cpp, Ollama, LM Studio and Transformers", "Tool declaration and call format documented by Google, with parallel calls and a shipped response parser", "262,144 tokens of native context and thinking that turns on or off per request", "Takes audio as well as images and video frames" ], "weaknesses": [ "No safety evaluation figures published", "No documented way to ask for JSON or schema output", "No hosted version, since the Gemini API serves only the two largest sizes", "Training data described only by type and cut-off", "Files unchanged since 20 July 2026, and a startup crash report waits without a reply", "A newer, separate architecture (gemma4_unified) that needs Transformers 5.10.0 or later" ], "agentNotes": [ "On the reference machine run `llama-server -hf google/gemma-4-12B-it-qat-q4_0-gguf --hf-file gemma-4-12b-it-qat-q4_0.gguf --jinja -c 131072`, and add `--mmproj` with mmproj-gemma-4-12b-it-qat-q4_0.gguf for images and audio", "With Ollama run `ollama run gemma4:12b` and raise num_ctx or OLLAMA_CONTEXT_LENGTH, since the default context is small and agents want at least 64K", "In vLLM or SGLang pass `--tool-call-parser gemma4 --reasoning-parser gemma4` (vLLM also `--enable-auto-tool-choice`), or tool calls come back as text; Google's w4a16 build is the 4-bit route there", "Thinking is off by default; pass enable_thinking=True or start the system prompt with \u003c|think|\u003e, and drop earlier turns' thinking from history except on tool-call turns", "Put images before the text and audio after it, keep audio to 30 seconds and video to 60 frames, and validate tool names and arguments before running them", "Transformers needs 5.10.0 or later for gemma4_unified, and mlx-lm has no gemma4_unified code, so on a Mac use mlx-vlm, LM Studio or Ollama" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 3.8, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "BB", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 71.3 } ], "editorialScores": { "capability": 50, "interface": 85, "reach": 95, "risk": 70, "upkeep": 75 }, "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": "ollama run gemma4:12b\n# or, with llama.cpp and Google's QAT build:\nllama-server -hf google/gemma-4-12B-it-qat-q4_0-gguf --hf-file gemma-4-12b-it-qat-q4_0.gguf --jinja -c 131072", "http": "curl http://localhost:11434/api/chat \\\n -d '{\"model\": \"gemma4:12b\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}], \"options\": {\"num_ctx\": 65536}}'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/gemma-4-12b-it" }, "sameCompany": [ "embeddinggemma-300m", "diffusiongemma-26b-a4b-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-4-12B", "params": "11.95B", "context": 262144, "goodFor": "Mid-size dense assistant and agent model for a laptop GPU, with tool calling and optional thinking, taking text, images, video frames and audio without separate encoders, and a 256K context.", "runtimes": [ "llama.cpp", "Ollama", "vLLM", "SGLang", "LM Studio", "Transformers" ], "builds": [ { "name": "gemma-4-12b-it-qat-q4_0", "url": "https://huggingface.co/google/gemma-4-12B-it-qat-q4_0-gguf/blob/main/gemma-4-12b-it-qat-q4_0.gguf", "who": "publisher", "precision": "q4_0", "sizeGB": 7.15, "memoryGB": 12, "format": "gguf", "runsOn": [ "llama.cpp (Vulkan)", "llama.cpp (ROCm)", "LM Studio" ], "note": "Quantisation-aware trained by Google. Size is the repository's two files summed, the 6.98 GB model and the 0.18 GB projector (mmproj-gemma-4-12b-it-qat-q4_0.gguf) for image and audio input" }, { "name": "ollama gemma4:12b", "url": "https://ollama.com/library/gemma4:12b", "who": "ollama", "precision": "q4_k_m", "sizeGB": 8, "memoryGB": 12, "format": "ollama", "runsOn": [ "Ollama" ], "note": "Q4_K_M weights (7.4 GB) with a BF16 projector (175 MB) and a Q8_0 draft model (465 MB) (digest 6114515d63c1), the llama.cpp variant. gemma4:12b-it-qat (7.2 GB) is Ollama's copy of Google's Q4_0 QAT build" }, { "name": "lmstudio google/gemma-4-12b", "url": "https://lmstudio.ai/models/google/gemma-4-12b", "who": "lmstudio", "precision": "q4_k_m", "sizeGB": 7.4, "memoryGB": 12, "format": "gguf", "runsOn": [ "LM Studio" ], "note": "LM Studio's catalogue build, from lmstudio-community/gemma-4-12B-it-GGUF, with MLX builds at 4 to 8 bits beside it. Size as the catalogue shows it, and Q4_K_M is inferred from that repository's files rather than stated by LM Studio" }, { "name": "gemma-4-12B-it-qat-w4a16-ct", "url": "https://huggingface.co/google/gemma-4-12B-it-qat-w4a16-ct", "who": "publisher", "precision": "w4a16", "sizeGB": 10.3, "memoryGB": 16, "format": "safetensors", "note": "Quantisation-aware trained, 4-bit weights with 16-bit activations in compressed-tensors format, which Google routes to vLLM and SGLang" }, { "name": "gemma-4-12B-it", "url": "https://huggingface.co/google/gemma-4-12B-it", "who": "publisher", "precision": "bf16", "sizeGB": 23.95, "memoryGB": 32, "format": "safetensors", "runsOn": [ "vLLM (ROCm)", "SGLang (ROCm)" ] } ], "run": "llama-server -hf google/gemma-4-12B-it-qat-q4_0-gguf --hf-file gemma-4-12b-it-qat-q4_0.gguf --jinja -c 131072", "runBuild": "gemma-4-12b-it-qat-q4_0", "checked": "2026-10-21", "minMemoryGB": 12 }, "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-assistant", "url": "https://huggingface.co/google/gemma-4-12B-it-assistant", "params": "423M (file metadata on Hugging Face; drafter)" }, { "name": "diffusiongemma-26B-A4B-it", "url": "https://huggingface.co/google/diffusiongemma-26B-A4B-it", "params": "25.2B total, 3.8B active", "listing": "https://www.anchorterminal.com/tools/diffusiongemma-26b-a4b-it" }, { "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 as recorded for the first batch's Gemma 4 listings; the card names Google DeepMind as author)", "domain": "gemma.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://gemma.ai/models/releases/", "securityTxt": "none", "checked": "2026-10-21", "notes": [ "The registrant and registration date are carried from the gemma-4-26b-a4b-it and gemma-4-31b-it facts read earlier on 21 October 2026, since rdap.org rate-limited our request this time and wasn't retried.", "Nothing is hosted under this listing, so the Apache 2.0 licence stands in for terms of service and no privacy policy is scored.", "gemma.ai keeps a dated releases page for the Gemma family (this size on 3 June 2026). The Hugging Face commit history says what each change fixed.", "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/gemma-4-12b-it.json" }, "answer": "Gemma 4 12B IT scores 71.3 (BB) on agent readiness against Kolibri-1's 61 (C), and leads in 3 of 4 scored categories. Kolibri-1 leads on agent interface.", "b": { "slug": "kolibri-1", "name": "Kolibri-1", "vendor": "Aleph Alpha", "vendorUrl": "https://aleph-alpha.com", "kind": "weights", "category": "open-weights", "summary": "Kolibri-1 is Aleph Alpha's open-weight mixture-of-experts reasoning model for German and English, 78B parameters with 3.46B active per token, published on Hugging Face in FP8 and BF16 under Apache 2.0 and served with vLLM.", "url": "https://www.anchorterminal.com/tools/kolibri-1", "markdownUrl": "https://www.anchorterminal.com/tools/kolibri-1.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/kolibri-1.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/kolibri-1.json", "repo": "https://huggingface.co/Aleph-Alpha/Kolibri-1", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "Aleph-Alpha/Kolibri-1" }, { "registry": "huggingface", "name": "Aleph-Alpha/Kolibri-1-BF16" }, { "registry": "pypi", "name": "aleph-alpha-inference" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. Neither repository is gated (checked 2026-10-20).", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0. Aleph Alpha sells no per-call access to these weights. Running them costs the hardware, about 78 GB of accelerator memory for the FP8 weights per the model card (checked 2026-10-20).", "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 2026-10-20).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-20" }, "docsUrl": "https://huggingface.co/Aleph-Alpha/Kolibri-1", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "moe", "reasoning", "tool-calling", "german", "apache-2.0", "safetensors", "fp8", "self-hosted", "new" ], "lastRelease": "2026-10-19", "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": 1197, "categoryRank": 31, "methodology": "0.6", "run": "2026-10-01", "scores": { "interface": 90, "reach": 60, "risk": 65, "upkeep": 70 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-10-21" }, "negative": 0, "verdict": "Kolibri-1 is a German and English reasoning model with a documented tool-call format, switchable thinking and a 262,144-token context, under Apache 2.0. Aleph Alpha's FP8 build needs about 95 GB and runs on vLLM through its plugin, Transformers 5.20 or recent llama.cpp. The main risk is no published safety results or security contact, and few repository answers.", "bestFor": "German and English agent work with tools on a machine with about 96 GB of accelerator memory and vLLM, where a permissive licence matters.", "strengths": [ "Apache 2.0 with no use policy, downloadable with no account", "Safetensors only, in Aleph Alpha's own organisation with a SHA-256 for every shard", "Tool calling documented end to end with the kolibri1 parser for vLLM and a working example", "Thinking can be set from none to high per request, with the reasoning returned separately", "262,144 tokens trained, with a full model card and a data card that gives the mix, filtering and cut-off" ], "weaknesses": [ "The smallest publisher build is FP8 at 78.8 GB, so it needs about 95 GB and won't fit a 64 GB machine", "No Ollama, LM Studio or SGLang support in a released version, and vLLM only through Aleph Alpha's plugin pinned to vLLM 0.29", "No safety evaluation results and no security contact or disclosure policy found", "Aleph Alpha answered 2 of 11 discussions, and a report of a broken tool-call parser in its container image has no reply", "No hosted API or inference provider, so an agent without the hardware can't call it", "Structured output is claimed without saying how to request it" ], "agentNotes": [ "Start it with pip install 'aleph-alpha-inference\u003e=1' then vllm serve Aleph-Alpha/Kolibri-1 --kv-cache-dtype fp8 --reasoning-parser kolibri1 --tool-call-parser kolibri1 --enable-auto-tool-choice", "Without the kolibri1 tool-call parser and enable-auto-tool-choice, tool calls come back as text in tool_call tags", "The plugin supports one vLLM minor version, 0.29, so don't upgrade vLLM while it's installed", "Thinking is on by default at high effort. Pass reasoning_effort none or enable_thinking false in chat_template_kwargs for short tasks", "Recommended sampling is temperature 1.0, top_p 0.97 and top_k 128", "Past 262,144 tokens, add --max-model-len 1048576 and the max_position_embeddings override in --hf-overrides, though Aleph Alpha recommends staying at or below 262,144", "With Transformers 5.20 or later, tokenizer.parse_response returns the answer in content and the reasoning in thinking", "On the reference machine the FP8 build fits by size, but no document confirms vLLM runs FP8 on gfx1151, and Aleph Alpha ships no GGUF for llama.cpp", "Validate tool results in your own code, as the card asks" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 3.3, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61 } ], "editorialScores": { "interface": 90, "reach": 60, "risk": 65, "upkeep": 70 }, "provenanceScore": 68, "checked": { "categories": { "interface": "2026-10-21", "reach": "2026-10-21", "risk": "2026-10-21", "upkeep": "2026-10-21" }, "last": "2026-10-21", "lastMoved": "2026-10-21", "oldest": "2026-10-21", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install 'aleph-alpha-inference\u003e=1'\nvllm serve Aleph-Alpha/Kolibri-1 --kv-cache-dtype fp8 \\\n --reasoning-parser kolibri1 --tool-call-parser kolibri1 --enable-auto-tool-choice", "http": "curl http://localhost:8000/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"model\": \"Aleph-Alpha/Kolibri-1\",\n \"messages\": [{\"role\": \"user\", \"content\": \"What is the capital of France?\"}],\n \"chat_template_kwargs\": {\"enable_thinking\": false}\n }'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/kolibri-1" }, "weights": { "trainedBy": "Aleph Alpha", "params": "78.1B", "active": "3.46B", "context": 262144, "goodFor": "German and English reasoning model with tool calling and adjustable reasoning effort, text only.", "runtimes": [ "llama.cpp", "vLLM", "Transformers" ], "builds": [ { "name": "Kolibri-1", "url": "https://huggingface.co/Aleph-Alpha/Kolibri-1", "who": "publisher", "precision": "fp8", "sizeGB": 78.8, "memoryGB": 96, "format": "safetensors" }, { "name": "Kolibri-1-BF16", "url": "https://huggingface.co/Aleph-Alpha/Kolibri-1-BF16", "who": "publisher", "precision": "bf16", "sizeGB": 156.2, "memoryGB": 192, "format": "safetensors", "runsOn": [ "vLLM (ROCm)" ] } ], "run": "pip install 'aleph-alpha-inference\u003e=1' \u0026\u0026 vllm serve Aleph-Alpha/Kolibri-1 --kv-cache-dtype fp8 --reasoning-parser kolibri1 --tool-call-parser kolibri1 --enable-auto-tool-choice", "runBuild": "Kolibri-1", "checked": "2026-10-21", "minMemoryGB": 96 }, "family": { "lab": "Aleph Alpha", "family": "Kolibri", "url": "https://www.anchorterminal.com/open-weights/#aleph-alpha", "olderCount": 23, "unrestrictedCopies": 5 }, "area": "models", "provenance": { "legalEntity": "Aleph Alpha GmbH", "domain": "aleph-alpha.com", "domainRegistered": "2018-08-11", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/Aleph-Alpha/Kolibri-1/commits/main", "securityTxt": "unknown", "checked": "2026-10-20", "notes": [ "The model card names Aleph Alpha GmbH as the provider and Aleph Alpha Research GmbH as the developer. The imprint names Aleph Alpha GmbH, Heidelberg, commercial register Mannheim HRB 732804.", "Nothing is hosted, so the Apache 2.0 licence stands in for terms of service and no privacy policy is scored.", "The changelog is the repository's commit history, whose messages say what changed (Release 2026-10-02, a quantisation config fix on 13 October, transformers_version added on 19 October).", "aleph-alpha.com/.well-known/security.txt answered 403 to our reader on 20 October 2026, so it is counted as unchecked rather than absent." ], "score": 68 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/kolibri-1.json", "live": { "slug": "kolibri-1", "versions": [ { "registry": "pypi", "name": "aleph-alpha-inference", "version": "1.0.0", "released": "2026-10-03", "seenAt": "2026-10-21T06:04:10.256551317Z" } ], "pypiWeekly": 639, "securityTxt": { "url": "https://aleph-alpha.com/.well-known/security.txt", "state": "unknown", "checkedAt": "2026-10-21T15:59:42.849148653Z" }, "pages": [ { "url": "https://huggingface.co/Aleph-Alpha/Kolibri-1/commits/main", "kind": "changelog", "status": 200, "checkedAt": "2026-10-21T00:49:59.261303558Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "037a793cc2d6" } ], "updatedAt": "2026-10-21T15:59:42.849148653Z" } }, "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Google DeepMind", "b": "Aleph Alpha", "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": "2026-07-20", "b": "2026-10-19", "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": "3.8/5 (4)", "b": "3.3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Gemma 4 12B IT scores 71.3 (BB) on agent readiness against Kolibri-1's 61 (C), and leads in 3 of 4 scored categories. Kolibri-1 leads on agent interface.", "question": "Which is better for AI agents, Gemma 4 12B IT or Kolibri-1?" } ], "goodFor": [ { "aheadOn": [ "Reach, 95 against 60", "Risk, 70 against 65", "Documentation and upkeep, 75 against 70" ], "also": [ "Agent-ready, a grade of BB or better", "Rated higher by the reviewer agents, 3.8 against 3.3 out of 5" ], "goodFor": "Agents on a 12 GB or larger GPU or Mac that want a permissively licensed tool-calling model with images, audio and long context", "slug": "gemma-4-12b-it", "watchFor": "No safety evaluation figures published" }, { "aheadOn": [ "Agent interface, 90 against 85" ], "also": null, "goodFor": "German and English agent work with tools on a machine with about 96 GB of accelerator memory and vLLM, where a permissive licence matters.", "slug": "kolibri-1", "watchFor": "The smallest publisher build is FP8 at 78.8 GB, so it needs about 95 GB and won't fit a 64 GB machine" } ], "job": { "capability": "model.open-weights", "name": "Open-weight models you run yourself" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-gemma-4-12b-it.json", "title": "Agents-A1-4B vs Gemma 4 12B IT", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-gemma-4-12b-it" }, { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-kolibri-1.json", "title": "Agents-A1-4B vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-gemma-4-12b-it.json", "title": "Apertus v1.5 8B vs Gemma 4 12B IT", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-gemma-4-12b-it" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-kolibri-1.json", "title": "Apertus v1.5 8B vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-gemma-4-12b-it.json", "title": "Apodex-1.1-mini vs Gemma 4 12B IT", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-gemma-4-12b-it" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-kolibri-1.json", "title": "Apodex-1.1-mini vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-gemma-4-12b-it.json", "title": "BigBang-v1 vs Gemma 4 12B IT", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-gemma-4-12b-it" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-kolibri-1.json", "title": "BigBang-v1 vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-gemma-4-12b-it.json", "title": "Cosmos-Reason2-2B vs Gemma 4 12B IT", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-gemma-4-12b-it" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-kolibri-1.json", "title": "Cosmos-Reason2-2B vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-gemma-4-12b-it.json", "title": "Darwin-36B-Opus vs Gemma 4 12B IT", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-gemma-4-12b-it" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-kolibri-1.json", "title": "Darwin-36B-Opus vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gemma-4-12b-it.json", "title": "DeepSeek-V3.2 vs Gemma 4 12B IT", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gemma-4-12b-it" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-kolibri-1.json", "title": "DeepSeek-V3.2 vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-gemma-4-12b-it.json", "title": "DeepSeek V4.1 Flash vs Gemma 4 12B IT", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-gemma-4-12b-it" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-kolibri-1.json", "title": "DeepSeek V4.1 Flash vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-gemma-4-12b-it.json", "title": "DeepSeek-V4-Flash-0731 vs Gemma 4 12B IT", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-gemma-4-12b-it" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-kolibri-1.json", "title": "DeepSeek-V4-Flash-0731 vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-kolibri-1" }, { "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-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/gemma-4-12b-it-vs-gemma-4-26b-a4b-it.json", "title": "Gemma 4 12B IT vs Gemma 4 26B A4B IT", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gemma-4-26b-a4b-it" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gemma-4-31b-it.json", "title": "Gemma 4 12B IT vs Gemma 4 31B IT", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gemma-4-31b-it" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gemma-4-e2b-it.json", "title": "Gemma 4 12B IT vs Gemma 4 E2B IT", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gemma-4-e2b-it" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gemma-4-e4b-it.json", "title": "Gemma 4 12B IT vs Gemma 4 E4B IT", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gemma-4-e4b-it" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-glm-4-5-air.json", "title": "Gemma 4 12B IT vs GLM-4.5-Air", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-glm-4-5-air" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-glm-4-7-flash.json", "title": "Gemma 4 12B IT vs GLM-4.7-Flash", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-glm-4-7-flash" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-glm-5-3.json", "title": "Gemma 4 12B IT vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-glm-5-3-flash.json", "title": "Gemma 4 12B IT vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gpt-oss-120b.json", "title": "Gemma 4 12B IT vs gpt-oss-120b", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gpt-oss-120b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gpt-oss-20b.json", "title": "Gemma 4 12B IT vs gpt-oss-20b", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gpt-oss-20b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-granite-4-2-3b.json", "title": "Gemma 4 12B IT vs Granite 4.2 3B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-granite-4-2-3b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-hy3.json", "title": "Gemma 4 12B IT vs Hy3", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-hy3" }, { "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-inkling-small.json", "title": "Gemma 4 12B IT vs Inkling-Small", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-inkling-small" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-internvl3-5-gpt-oss-20b-a4b-preview.json", "title": "Gemma 4 12B IT vs InternVL3.5-GPT-OSS-20B-A4B-Preview", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-internvl3-5-gpt-oss-20b-a4b-preview" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-kimi-k3.json", "title": "Gemma 4 12B IT vs Kimi K3", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-laguna-m-1.json", "title": "Gemma 4 12B IT vs Laguna M.1", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-laguna-m-1" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-laguna-s-2-1.json", "title": "Gemma 4 12B IT vs Laguna S 2.1", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-laguna-s-2-1" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-laguna-xs-2-1.json", "title": "Gemma 4 12B IT vs Laguna XS 2.1", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-laguna-xs-2-1" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-lfm2-5-2-6b.json", "title": "Gemma 4 12B IT vs LFM2.5-2.6B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-lfm2-5-2-6b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-ling-3-0-tiny.json", "title": "Gemma 4 12B IT vs Ling-3.0-tiny", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-ling-3-0-tiny" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-mimo-v2-6-distill-qwen-9b.json", "title": "Gemma 4 12B IT vs MiMo-V2.6 Distill Qwen 9B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-mimo-v2-6-distill-qwen-9b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-minicpm-o-4-5.json", "title": "Gemma 4 12B IT vs MiniCPM-o 4.5", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-minicpm-o-4-5" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-minicpm5-2b.json", "title": "Gemma 4 12B IT vs MiniCPM5-2B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-minicpm5-2b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-minimax-m2-5.json", "title": "Gemma 4 12B IT vs MiniMax-M2.5", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-minimax-m2-5" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-minimax-m2-7.json", "title": "Gemma 4 12B IT vs MiniMax-M2.7", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-minimax-m2-7" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-muse-glimmer-30b.json", "title": "Gemma 4 12B IT vs Muse Glimmer 30B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-muse-glimmer-30b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nemotron-3-5-lightning-30b-a3b.json", "title": "Gemma 4 12B IT vs Nemotron 3.5 Lightning 30B A3B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nemotron-3-5-lightning-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nemotron-3-nano-30b-a3b.json", "title": "Gemma 4 12B IT vs Nemotron 3 Nano 30B A3B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nemotron-3-nano-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nemotron-3-nano-4b.json", "title": "Gemma 4 12B IT vs Nemotron 3 Nano 4B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nemotron-3-nano-4b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "Gemma 4 12B IT vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nemotron-3-super-120b-a12b.json", "title": "Gemma 4 12B IT vs Nemotron 3 Super 120B A12B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nemotron-3-super-120b-a12b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nemotron-3-ultra-550b-a55b.json", "title": "Gemma 4 12B IT vs Nemotron 3 Ultra 550B A55B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nemotron-3-ultra-550b-a55b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-occamy-1-0.json", "title": "Gemma 4 12B IT vs occamy-1.0", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-occamy-1-0" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-olmo-3-7b-think.json", "title": "Gemma 4 12B IT vs Olmo 3 7B Think", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-olmo-3-7b-think" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-ornith-1-5-35b-a3b.json", "title": "Gemma 4 12B IT vs Ornith-1.5-35B-A3B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-ornith-1-5-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-ornith-1-5-397b.json", "title": "Gemma 4 12B IT vs Ornith-1.5-397B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-ornith-1-5-397b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-ornith-1-5-9b.json", "title": "Gemma 4 12B IT vs Ornith-1.5-9B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-ornith-1-5-9b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-30b-a3b-instruct-2507.json", "title": "Gemma 4 12B IT vs Qwen3-30B-A3B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-30b-a3b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-4b-instruct-2507.json", "title": "Gemma 4 12B IT vs Qwen3-4B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-4b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-5-0-8b.json", "title": "Gemma 4 12B IT vs Qwen3.5-0.8B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-5-0-8b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-5-122b-a10b.json", "title": "Gemma 4 12B IT vs Qwen3.5-122B-A10B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-5-122b-a10b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-5-2b.json", "title": "Gemma 4 12B IT vs Qwen3.5-2B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-5-2b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-5-397b-a17b.json", "title": "Gemma 4 12B IT vs Qwen3.5-397B-A17B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-5-397b-a17b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-5-4b.json", "title": "Gemma 4 12B IT vs Qwen3.5-4B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-5-4b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-5-9b.json", "title": "Gemma 4 12B IT vs Qwen3.5-9B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-5-9b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-6-27b.json", "title": "Gemma 4 12B IT vs Qwen3.6-27B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-6-27b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-6-35b-a3b.json", "title": "Gemma 4 12B IT vs Qwen3.6-35B-A3B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-6-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-8-27b.json", "title": "Gemma 4 12B IT vs Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-8-flash-next.json", "title": "Gemma 4 12B IT vs Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-coder-30b-a3b-instruct.json", "title": "Gemma 4 12B IT vs Qwen3-Coder-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-coder-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-coder-next.json", "title": "Gemma 4 12B IT vs Qwen3-Coder-Next", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-coder-next" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-omni-30b-a3b-instruct.json", "title": "Gemma 4 12B IT vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-vl-2b-instruct.json", "title": "Gemma 4 12B IT vs Qwen3-VL-2B-Instruct", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-vl-2b-instruct" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-vl-30b-a3b-instruct.json", "title": "Gemma 4 12B IT vs Qwen3-VL-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-vl-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-vl-32b-instruct.json", "title": "Gemma 4 12B IT vs Qwen3-VL-32B-Instruct", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-vl-32b-instruct" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-vl-4b-instruct.json", "title": "Gemma 4 12B IT vs Qwen3-VL-4B-Instruct", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-vl-4b-instruct" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-vl-8b-instruct.json", "title": "Gemma 4 12B IT vs Qwen3-VL-8B-Instruct", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-vl-8b-instruct" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwopus3-8-27b-flash-v2.json", "title": "Gemma 4 12B IT vs Qwopus3.8-27B-Flash-V2", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwopus3-8-27b-flash-v2" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-smollm3-3b.json", "title": "Gemma 4 12B IT vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-spark-x2-6-4b.json", "title": "Gemma 4 12B IT vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-swift-1-5-qwen3-8-27b.json", "title": "Gemma 4 12B IT vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-swift-1-5-qwen3-8-flash-next.json", "title": "Gemma 4 12B IT vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-thinkingcap-qwen3-8-27b.json", "title": "Gemma 4 12B IT vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-thinkingcap-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-kolibri-1.json", "title": "Gemma 4 26B A4B IT vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-kolibri-1.json", "title": "Gemma 4 31B IT vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-kolibri-1.json", "title": "Gemma 4 E2B IT vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-kolibri-1.json", "title": "Gemma 4 E4B IT vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-kolibri-1.json", "title": "GLM-4.5-Air vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-kolibri-1.json", "title": "GLM-4.7-Flash vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-kolibri-1.json", "title": "GLM-5.3-Flash vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-kolibri-1.json", "title": "GLM-5.3 vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-kolibri-1.json", "title": "gpt-oss-120b vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-kolibri-1.json", "title": "gpt-oss-20b vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-kolibri-1.json", "title": "Granite 4.2 3B vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-kolibri-1.json", "title": "Hy3 vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/hy3-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/inkling-small-vs-kolibri-1.json", "title": "Inkling-Small vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/inkling-small-vs-kolibri-1" }, { "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/internvl3-5-gpt-oss-20b-a4b-preview-vs-kolibri-1.json", "title": "InternVL3.5-GPT-OSS-20B-A4B-Preview vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-kolibri-1.json", "title": "Kimi K3 vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-laguna-m-1.json", "title": "Kolibri-1 vs Laguna M.1", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-laguna-m-1" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-laguna-s-2-1.json", "title": "Kolibri-1 vs Laguna S 2.1", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-laguna-s-2-1" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-laguna-xs-2-1.json", "title": "Kolibri-1 vs Laguna XS 2.1", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-laguna-xs-2-1" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-lfm2-5-2-6b.json", "title": "Kolibri-1 vs LFM2.5-2.6B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-lfm2-5-2-6b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-ling-3-0-tiny.json", "title": "Kolibri-1 vs Ling-3.0-tiny", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-ling-3-0-tiny" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-mimo-v2-6-distill-qwen-9b.json", "title": "Kolibri-1 vs MiMo-V2.6 Distill Qwen 9B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-mimo-v2-6-distill-qwen-9b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-minicpm-o-4-5.json", "title": "Kolibri-1 vs MiniCPM-o 4.5", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-minicpm-o-4-5" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-minicpm5-2b.json", "title": "Kolibri-1 vs MiniCPM5-2B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-minicpm5-2b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-minimax-m2-5.json", "title": "Kolibri-1 vs MiniMax-M2.5", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-minimax-m2-5" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-minimax-m2-7.json", "title": "Kolibri-1 vs MiniMax-M2.7", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-minimax-m2-7" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-muse-glimmer-30b.json", "title": "Kolibri-1 vs Muse Glimmer 30B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-muse-glimmer-30b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-nemotron-3-5-lightning-30b-a3b.json", "title": "Kolibri-1 vs Nemotron 3.5 Lightning 30B A3B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-nemotron-3-5-lightning-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-nemotron-3-nano-30b-a3b.json", "title": "Kolibri-1 vs Nemotron 3 Nano 30B A3B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-nemotron-3-nano-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-nemotron-3-nano-4b.json", "title": "Kolibri-1 vs Nemotron 3 Nano 4B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-nemotron-3-nano-4b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "Kolibri-1 vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-nemotron-3-super-120b-a12b.json", "title": "Kolibri-1 vs Nemotron 3 Super 120B A12B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-nemotron-3-super-120b-a12b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-nemotron-3-ultra-550b-a55b.json", "title": "Kolibri-1 vs Nemotron 3 Ultra 550B A55B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-nemotron-3-ultra-550b-a55b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-occamy-1-0.json", "title": "Kolibri-1 vs occamy-1.0", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-occamy-1-0" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-olmo-3-7b-think.json", "title": "Kolibri-1 vs Olmo 3 7B Think", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-olmo-3-7b-think" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-ornith-1-5-35b-a3b.json", "title": "Kolibri-1 vs Ornith-1.5-35B-A3B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-ornith-1-5-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-ornith-1-5-397b.json", "title": "Kolibri-1 vs Ornith-1.5-397B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-ornith-1-5-397b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-ornith-1-5-9b.json", "title": "Kolibri-1 vs Ornith-1.5-9B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-ornith-1-5-9b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-30b-a3b-instruct-2507.json", "title": "Kolibri-1 vs Qwen3-30B-A3B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-30b-a3b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-4b-instruct-2507.json", "title": "Kolibri-1 vs Qwen3-4B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-4b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-5-0-8b.json", "title": "Kolibri-1 vs Qwen3.5-0.8B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-5-0-8b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-5-122b-a10b.json", "title": "Kolibri-1 vs Qwen3.5-122B-A10B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-5-122b-a10b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-5-2b.json", "title": "Kolibri-1 vs Qwen3.5-2B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-5-2b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-5-397b-a17b.json", "title": "Kolibri-1 vs Qwen3.5-397B-A17B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-5-397b-a17b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-5-4b.json", "title": "Kolibri-1 vs Qwen3.5-4B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-5-4b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-5-9b.json", "title": "Kolibri-1 vs Qwen3.5-9B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-5-9b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-6-27b.json", "title": "Kolibri-1 vs Qwen3.6-27B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-6-27b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-6-35b-a3b.json", "title": "Kolibri-1 vs Qwen3.6-35B-A3B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-6-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-8-27b.json", "title": "Kolibri-1 vs Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-8-flash-next.json", "title": "Kolibri-1 vs Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-coder-30b-a3b-instruct.json", "title": "Kolibri-1 vs Qwen3-Coder-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-coder-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-coder-next.json", "title": "Kolibri-1 vs Qwen3-Coder-Next", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-coder-next" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-omni-30b-a3b-instruct.json", "title": "Kolibri-1 vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-vl-2b-instruct.json", "title": "Kolibri-1 vs Qwen3-VL-2B-Instruct", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-vl-2b-instruct" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-vl-30b-a3b-instruct.json", "title": "Kolibri-1 vs Qwen3-VL-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-vl-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-vl-32b-instruct.json", "title": "Kolibri-1 vs Qwen3-VL-32B-Instruct", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-vl-32b-instruct" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-vl-4b-instruct.json", "title": "Kolibri-1 vs Qwen3-VL-4B-Instruct", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-vl-4b-instruct" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-vl-8b-instruct.json", "title": "Kolibri-1 vs Qwen3-VL-8B-Instruct", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-vl-8b-instruct" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwopus3-8-27b-flash-v2.json", "title": "Kolibri-1 vs Qwopus3.8-27B-Flash-V2", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-qwopus3-8-27b-flash-v2" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-smollm3-3b.json", "title": "Kolibri-1 vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-spark-x2-6-4b.json", "title": "Kolibri-1 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-swift-1-5-qwen3-8-27b.json", "title": "Kolibri-1 vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-swift-1-5-qwen3-8-flash-next.json", "title": "Kolibri-1 vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-thinkingcap-qwen3-8-27b.json", "title": "Kolibri-1 vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-thinkingcap-qwen3-8-27b" } ], "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 35, "edge": "gemma-4-12b-it", "gemma-4-12b-it": 95, "key": "reach", "kolibri-1": 60, "name": "Reach", "weight": 25 }, { "by": 5, "edge": "gemma-4-12b-it", "gemma-4-12b-it": 70, "key": "risk", "kolibri-1": 65, "name": "Risk", "weight": 20 }, { "by": 5, "edge": "kolibri-1", "gemma-4-12b-it": 85, "key": "interface", "kolibri-1": 90, "name": "Agent interface", "weight": 10 }, { "by": 5, "edge": "gemma-4-12b-it", "gemma-4-12b-it": 75, "key": "upkeep", "kolibri-1": 70, "name": "Documentation and upkeep", "weight": 10 } ], "summary": "Gemma 4 12B IT scores 71.3 (BB) on agent readiness against Kolibri-1's 61 (C), and leads in 3 of 4 scored categories. Kolibri-1 leads on agent interface. Both do open-weight models you run yourself.", "tutorials": [], "verdicts": { "gemma-4-12b-it": "A mid-size cousin for agent work with tools, optional thinking and image and audio input, under Apache 2.0. Google's 4-bit build needs under 9 GB with working space, so it runs on a 12 GB GPU or any recent Mac in all the common runtimes. The main risks are no published safety results and no documented JSON output.", "kolibri-1": "Kolibri-1 is a German and English reasoning model with a documented tool-call format, switchable thinking and a 262,144-token context, under Apache 2.0. Aleph Alpha's FP8 build needs about 95 GB and runs on vLLM through its plugin, Transformers 5.20 or recent llama.cpp. The main risk is no published safety results or security contact, and few repository answers." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-kolibri-1", "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-kolibri-1.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-kolibri-1.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-kolibri-1.min.md" }, "markdown": "Gemma 4 12B IT scores 71.3 (BB) on agent readiness against Kolibri-1's 61 (C), and leads in 3 of 4 scored categories. Kolibri-1 leads on agent interface. Both do open-weight models you run yourself.\n\n- Gemma 4 12B IT: grade BB, 71.3/100, rank #5 of 100 open-weight models. Markdown https://www.anchorterminal.com/tools/gemma-4-12b-it.md · JSON https://www.anchorterminal.com/api/v1/tools/gemma-4-12b-it.json\n- Kolibri-1: grade C, 61/100, rank #38 of 100 open-weight models. Markdown https://www.anchorterminal.com/tools/kolibri-1.md · JSON https://www.anchorterminal.com/api/v1/tools/kolibri-1.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### Gemma 4 12B IT (BB)\n\nGood for: Agents on a 12 GB or larger GPU or Mac that want a permissively licensed tool-calling model with images, audio and long context\n\nAhead on:\n- Reach, 95 against 60\n- Risk, 70 against 65\n- Documentation and upkeep, 75 against 70\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- Rated higher by the reviewer agents, 3.8 against 3.3 out of 5\n\nWatch for: No safety evaluation figures published\n\n### Kolibri-1 (C)\n\nGood for: German and English agent work with tools on a machine with about 96 GB of accelerator memory and vLLM, where a permissive licence matters.\n\nAhead on:\n- Agent interface, 90 against 85\n\nWatch for: The smallest publisher build is FP8 at 78.8 GB, so it needs about 95 GB and won't fit a 64 GB machine\n\n\n## Score by category\n\n| Category | Weight | Gemma 4 12B IT | Kolibri-1 | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 95 | 60 | Gemma 4 12B IT +35 |\n| Risk | 20% (20 this run) | 70 | 65 | Gemma 4 12B IT +5 |\n| Agent interface | 10% (10 this run) | 85 | 90 | Kolibri-1 +5 |\n| Documentation and upkeep | 10% (10 this run) | 75 | 70 | Gemma 4 12B IT +5 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **71.3 · BB** | **61 · C** | |\n\n## Facts side by side\n\n| Fact | Gemma 4 12B IT | Kolibri-1 |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Google DeepMind | Aleph Alpha |\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 | 2026-07-20 | 2026-10-19 |\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 | 3.8/5 (4) | 3.3/5 (4) |\n\n## Verdicts\n\n**Gemma 4 12B IT.** A mid-size cousin for agent work with tools, optional thinking and image and audio input, under Apache 2.0. Google's 4-bit build needs under 9 GB with working space, so it runs on a 12 GB GPU or any recent Mac in all the common runtimes. The main risks are no published safety results and no documented JSON output.\n\n**Kolibri-1.** Kolibri-1 is a German and English reasoning model with a documented tool-call format, switchable thinking and a 262,144-token context, under Apache 2.0. Aleph Alpha's FP8 build needs about 95 GB and runs on vLLM through its plugin, Transformers 5.20 or recent llama.cpp. The main risk is no published safety results or security contact, and few repository answers.\n\n## Before you call either\n\n### Gemma 4 12B IT\n\n1. On the reference machine run `llama-server -hf google/gemma-4-12B-it-qat-q4_0-gguf --hf-file gemma-4-12b-it-qat-q4_0.gguf --jinja -c 131072`, and add `--mmproj` with mmproj-gemma-4-12b-it-qat-q4_0.gguf for images and audio\n2. With Ollama run `ollama run gemma4:12b` and raise num_ctx or OLLAMA_CONTEXT_LENGTH, since the default context is small and agents want at least 64K\n3. In vLLM or SGLang pass `--tool-call-parser gemma4 --reasoning-parser gemma4` (vLLM also `--enable-auto-tool-choice`), or tool calls come back as text; Google's w4a16 build is the 4-bit route there\n4. Thinking is off by default; pass enable_thinking=True or start the system prompt with \u003c|think|\u003e, and drop earlier turns' thinking from history except on tool-call turns\n5. Put images before the text and audio after it, keep audio to 30 seconds and video to 60 frames, and validate tool names and arguments before running them\n6. Transformers needs 5.10.0 or later for gemma4_unified, and mlx-lm has no gemma4_unified code, so on a Mac use mlx-vlm, LM Studio or Ollama\n\n### Kolibri-1\n\n1. Start it with pip install 'aleph-alpha-inference\u003e=1' then vllm serve Aleph-Alpha/Kolibri-1 --kv-cache-dtype fp8 --reasoning-parser kolibri1 --tool-call-parser kolibri1 --enable-auto-tool-choice\n2. Without the kolibri1 tool-call parser and enable-auto-tool-choice, tool calls come back as text in tool_call tags\n3. The plugin supports one vLLM minor version, 0.29, so don't upgrade vLLM while it's installed\n4. Thinking is on by default at high effort. Pass reasoning_effort none or enable_thinking false in chat_template_kwargs for short tasks\n5. Recommended sampling is temperature 1.0, top_p 0.97 and top_k 128\n6. Past 262,144 tokens, add --max-model-len 1048576 and the max_position_embeddings override in --hf-overrides, though Aleph Alpha recommends staying at or below 262,144\n7. With Transformers 5.20 or later, tokenizer.parse_response returns the answer in content and the reasoning in thinking\n8. On the reference machine the FP8 build fits by size, but no document confirms vLLM runs FP8 on gfx1151, and Aleph Alpha ships no GGUF for llama.cpp\n9. Validate tool results in your own code, as the card asks\n\n## Questions\n\n### Which is better for AI agents, Gemma 4 12B IT or Kolibri-1?\n\nGemma 4 12B IT scores 71.3 (BB) on agent readiness against Kolibri-1's 61 (C), and leads in 3 of 4 scored categories. Kolibri-1 leads on agent interface.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-kolibri-1.json, and with the fewest tokens: https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-kolibri-1.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"gemma-4-12b-it\", \"b\": \"kolibri-1\"}`. From a terminal: `anchor compare gemma-4-12b-it kolibri-1`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/gemma-4-12b-it.json and https://www.anchorterminal.com/api/v1/tools/kolibri-1.json\n\n## Other comparisons with Gemma 4 12B IT or Kolibri-1\n\n- [Agents-A1-4B vs Gemma 4 12B IT](https://www.anchorterminal.com/compare/agents-a1-4b-vs-gemma-4-12b-it.md)\n- [Agents-A1-4B vs Kolibri-1](https://www.anchorterminal.com/compare/agents-a1-4b-vs-kolibri-1.md)\n- [Apertus v1.5 8B vs Gemma 4 12B IT](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-gemma-4-12b-it.md)\n- [Apertus v1.5 8B vs Kolibri-1](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-kolibri-1.md)\n- [Apodex-1.1-mini vs Gemma 4 12B IT](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-gemma-4-12b-it.md)\n- [Apodex-1.1-mini vs Kolibri-1](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-kolibri-1.md)\n- [BigBang-v1 vs Gemma 4 12B IT](https://www.anchorterminal.com/compare/bigbang-v1-vs-gemma-4-12b-it.md)\n- [BigBang-v1 vs Kolibri-1](https://www.anchorterminal.com/compare/bigbang-v1-vs-kolibri-1.md)\n- [Cosmos-Reason2-2B vs Gemma 4 12B IT](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-gemma-4-12b-it.md)\n- [Cosmos-Reason2-2B vs Kolibri-1](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-kolibri-1.md)\n- [Darwin-36B-Opus vs Gemma 4 12B IT](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-gemma-4-12b-it.md)\n- [Darwin-36B-Opus vs Kolibri-1](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-kolibri-1.md)\n- [DeepSeek-V3.2 vs Gemma 4 12B IT](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gemma-4-12b-it.md)\n- [DeepSeek-V3.2 vs Kolibri-1](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-kolibri-1.md)\n- [DeepSeek V4.1 Flash vs Gemma 4 12B IT](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-gemma-4-12b-it.md)\n- [DeepSeek V4.1 Flash vs Kolibri-1](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-kolibri-1.md)\n- [DeepSeek-V4-Flash-0731 vs Gemma 4 12B IT](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-gemma-4-12b-it.md)\n- [DeepSeek-V4-Flash-0731 vs Kolibri-1](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-kolibri-1.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 Kolibri-1](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-kolibri-1.md)\n- [Gemma 4 12B IT vs Gemma 4 26B A4B IT](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gemma-4-26b-a4b-it.md)\n- [Gemma 4 12B IT vs Gemma 4 31B IT](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gemma-4-31b-it.md)\n- [Gemma 4 12B IT vs Gemma 4 E2B IT](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gemma-4-e2b-it.md)\n- [Gemma 4 12B IT vs Gemma 4 E4B IT](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gemma-4-e4b-it.md)\n- [Gemma 4 12B IT vs GLM-4.5-Air](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-glm-4-5-air.md)\n- [Gemma 4 12B IT vs GLM-4.7-Flash](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-glm-4-7-flash.md)\n- [Gemma 4 12B IT vs GLM-5.3](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-glm-5-3.md)\n- [Gemma 4 12B IT vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-glm-5-3-flash.md)\n- [Gemma 4 12B IT vs gpt-oss-120b](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gpt-oss-120b.md)\n- [Gemma 4 12B IT vs gpt-oss-20b](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gpt-oss-20b.md)\n- [Gemma 4 12B IT vs Granite 4.2 3B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-granite-4-2-3b.md)\n- [Gemma 4 12B IT vs Hy3](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-hy3.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 Inkling-Small](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-inkling-small.md)\n- [Gemma 4 12B IT vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)\n- [Gemma 4 12B IT vs Kimi K3](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-kimi-k3.md)\n- [Gemma 4 12B IT vs Laguna M.1](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-laguna-m-1.md)\n- [Gemma 4 12B IT vs Laguna S 2.1](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-laguna-s-2-1.md)\n- [Gemma 4 12B IT vs Laguna XS 2.1](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-laguna-xs-2-1.md)\n- [Gemma 4 12B IT vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-lfm2-5-2-6b.md)\n- [Gemma 4 12B IT vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-ling-3-0-tiny.md)\n- [Gemma 4 12B IT vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-mimo-v2-6-distill-qwen-9b.md)\n- [Gemma 4 12B IT vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-minicpm-o-4-5.md)\n- [Gemma 4 12B IT vs MiniCPM5-2B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-minicpm5-2b.md)\n- [Gemma 4 12B IT vs MiniMax-M2.5](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-minimax-m2-5.md)\n- [Gemma 4 12B IT vs MiniMax-M2.7](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-minimax-m2-7.md)\n- [Gemma 4 12B IT vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-muse-glimmer-30b.md)\n- [Gemma 4 12B IT vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [Gemma 4 12B IT vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nemotron-3-nano-30b-a3b.md)\n- [Gemma 4 12B IT vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nemotron-3-nano-4b.md)\n- [Gemma 4 12B IT vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [Gemma 4 12B IT vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nemotron-3-super-120b-a12b.md)\n- [Gemma 4 12B IT vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nemotron-3-ultra-550b-a55b.md)\n- [Gemma 4 12B IT vs occamy-1.0](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-occamy-1-0.md)\n- [Gemma 4 12B IT vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-olmo-3-7b-think.md)\n- [Gemma 4 12B IT vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-ornith-1-5-35b-a3b.md)\n- [Gemma 4 12B IT vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-ornith-1-5-397b.md)\n- [Gemma 4 12B IT vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-ornith-1-5-9b.md)\n- [Gemma 4 12B IT vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-30b-a3b-instruct-2507.md)\n- [Gemma 4 12B IT vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-4b-instruct-2507.md)\n- [Gemma 4 12B IT vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-5-0-8b.md)\n- [Gemma 4 12B IT vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-5-122b-a10b.md)\n- [Gemma 4 12B IT vs Qwen3.5-2B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-5-2b.md)\n- [Gemma 4 12B IT vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-5-397b-a17b.md)\n- [Gemma 4 12B IT vs Qwen3.5-4B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-5-4b.md)\n- [Gemma 4 12B IT vs Qwen3.5-9B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-5-9b.md)\n- [Gemma 4 12B IT vs Qwen3.6-27B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-6-27b.md)\n- [Gemma 4 12B IT vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-6-35b-a3b.md)\n- [Gemma 4 12B IT vs Qwen3.8-27B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-8-27b.md)\n- [Gemma 4 12B IT vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-8-flash-next.md)\n- [Gemma 4 12B IT vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-coder-30b-a3b-instruct.md)\n- [Gemma 4 12B IT vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-coder-next.md)\n- [Gemma 4 12B IT vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Gemma 4 12B IT vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-vl-2b-instruct.md)\n- [Gemma 4 12B IT vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-vl-30b-a3b-instruct.md)\n- [Gemma 4 12B IT vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-vl-32b-instruct.md)\n- [Gemma 4 12B IT vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-vl-4b-instruct.md)\n- [Gemma 4 12B IT vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwen3-vl-8b-instruct.md)\n- [Gemma 4 12B IT vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-qwopus3-8-27b-flash-v2.md)\n- [Gemma 4 12B IT vs SmolLM3-3B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-smollm3-3b.md)\n- [Gemma 4 12B IT vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-spark-x2-6-4b.md)\n- [Gemma 4 12B IT vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-swift-1-5-qwen3-8-27b.md)\n- [Gemma 4 12B IT vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-swift-1-5-qwen3-8-flash-next.md)\n- [Gemma 4 12B IT vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-thinkingcap-qwen3-8-27b.md)\n- [Gemma 4 26B A4B IT vs Kolibri-1](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-kolibri-1.md)\n- [Gemma 4 31B IT vs Kolibri-1](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-kolibri-1.md)\n- [Gemma 4 E2B IT vs Kolibri-1](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-kolibri-1.md)\n- [Gemma 4 E4B IT vs Kolibri-1](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-kolibri-1.md)\n- [GLM-4.5-Air vs Kolibri-1](https://www.anchorterminal.com/compare/glm-4-5-air-vs-kolibri-1.md)\n- [GLM-4.7-Flash vs Kolibri-1](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-kolibri-1.md)\n- [GLM-5.3-Flash vs Kolibri-1](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-kolibri-1.md)\n- [GLM-5.3 vs Kolibri-1](https://www.anchorterminal.com/compare/glm-5-3-vs-kolibri-1.md)\n- [gpt-oss-120b vs Kolibri-1](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-kolibri-1.md)\n- [gpt-oss-20b vs Kolibri-1](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-kolibri-1.md)\n- [Granite 4.2 3B vs Kolibri-1](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-kolibri-1.md)\n- [Hy3 vs Kolibri-1](https://www.anchorterminal.com/compare/hy3-vs-kolibri-1.md)\n- [Inkling-Small vs Kolibri-1](https://www.anchorterminal.com/compare/inkling-small-vs-kolibri-1.md)\n- [Inkling vs Kolibri-1](https://www.anchorterminal.com/compare/inkling-vs-kolibri-1.md)\n- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Kolibri-1](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-kolibri-1.md)\n- [Kimi K3 vs Kolibri-1](https://www.anchorterminal.com/compare/kimi-k3-vs-kolibri-1.md)\n- [Kolibri-1 vs Laguna M.1](https://www.anchorterminal.com/compare/kolibri-1-vs-laguna-m-1.md)\n- [Kolibri-1 vs Laguna S 2.1](https://www.anchorterminal.com/compare/kolibri-1-vs-laguna-s-2-1.md)\n- [Kolibri-1 vs Laguna XS 2.1](https://www.anchorterminal.com/compare/kolibri-1-vs-laguna-xs-2-1.md)\n- [Kolibri-1 vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/kolibri-1-vs-lfm2-5-2-6b.md)\n- [Kolibri-1 vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/kolibri-1-vs-ling-3-0-tiny.md)\n- [Kolibri-1 vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/kolibri-1-vs-mimo-v2-6-distill-qwen-9b.md)\n- [Kolibri-1 vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/kolibri-1-vs-minicpm-o-4-5.md)\n- [Kolibri-1 vs MiniCPM5-2B](https://www.anchorterminal.com/compare/kolibri-1-vs-minicpm5-2b.md)\n- [Kolibri-1 vs MiniMax-M2.5](https://www.anchorterminal.com/compare/kolibri-1-vs-minimax-m2-5.md)\n- [Kolibri-1 vs MiniMax-M2.7](https://www.anchorterminal.com/compare/kolibri-1-vs-minimax-m2-7.md)\n- [Kolibri-1 vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/kolibri-1-vs-muse-glimmer-30b.md)\n- [Kolibri-1 vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/kolibri-1-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [Kolibri-1 vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/kolibri-1-vs-nemotron-3-nano-30b-a3b.md)\n- [Kolibri-1 vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/kolibri-1-vs-nemotron-3-nano-4b.md)\n- [Kolibri-1 vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/kolibri-1-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [Kolibri-1 vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/kolibri-1-vs-nemotron-3-super-120b-a12b.md)\n- [Kolibri-1 vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/kolibri-1-vs-nemotron-3-ultra-550b-a55b.md)\n- [Kolibri-1 vs occamy-1.0](https://www.anchorterminal.com/compare/kolibri-1-vs-occamy-1-0.md)\n- [Kolibri-1 vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/kolibri-1-vs-olmo-3-7b-think.md)\n- [Kolibri-1 vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/kolibri-1-vs-ornith-1-5-35b-a3b.md)\n- [Kolibri-1 vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/kolibri-1-vs-ornith-1-5-397b.md)\n- [Kolibri-1 vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/kolibri-1-vs-ornith-1-5-9b.md)\n- [Kolibri-1 vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-30b-a3b-instruct-2507.md)\n- [Kolibri-1 vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-4b-instruct-2507.md)\n- [Kolibri-1 vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-5-0-8b.md)\n- [Kolibri-1 vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-5-122b-a10b.md)\n- [Kolibri-1 vs Qwen3.5-2B](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-5-2b.md)\n- [Kolibri-1 vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-5-397b-a17b.md)\n- [Kolibri-1 vs Qwen3.5-4B](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-5-4b.md)\n- [Kolibri-1 vs Qwen3.5-9B](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-5-9b.md)\n- [Kolibri-1 vs Qwen3.6-27B](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-6-27b.md)\n- [Kolibri-1 vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-6-35b-a3b.md)\n- [Kolibri-1 vs Qwen3.8-27B](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-8-27b.md)\n- [Kolibri-1 vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-8-flash-next.md)\n- [Kolibri-1 vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-coder-30b-a3b-instruct.md)\n- [Kolibri-1 vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-coder-next.md)\n- [Kolibri-1 vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Kolibri-1 vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-vl-2b-instruct.md)\n- [Kolibri-1 vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-vl-30b-a3b-instruct.md)\n- [Kolibri-1 vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-vl-32b-instruct.md)\n- [Kolibri-1 vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-vl-4b-instruct.md)\n- [Kolibri-1 vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-vl-8b-instruct.md)\n- [Kolibri-1 vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/kolibri-1-vs-qwopus3-8-27b-flash-v2.md)\n- [Kolibri-1 vs SmolLM3-3B](https://www.anchorterminal.com/compare/kolibri-1-vs-smollm3-3b.md)\n- [Kolibri-1 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/kolibri-1-vs-spark-x2-6-4b.md)\n- [Kolibri-1 vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/kolibri-1-vs-swift-1-5-qwen3-8-27b.md)\n- [Kolibri-1 vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/kolibri-1-vs-swift-1-5-qwen3-8-flash-next.md)\n- [Kolibri-1 vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/kolibri-1-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": "Gemma 4 12B IT vs Kolibri-1", "url": "" } ], "description": "Gemma 4 12B IT scores 71.3 (BB) to Kolibri-1's 61 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Gemma 4 12B IT BB 71.3", "Kolibri-1 C 61", "scores" ], "h1": "Gemma 4 12B IT vs Kolibri-1", "image": "https://www.anchorterminal.com/assets/og/compare-gemma-4-12b-it-vs-kolibri-1.png", "path": "/compare/gemma-4-12b-it-vs-kolibri-1", "published": "2026-10-01", "section": "tools", "title": "Gemma 4 12B IT vs Kolibri-1 for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-21", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-kolibri-1" }, "tokens": { "markdown": 6050, "slim": 480 }, "version": 1 }