{ "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-10", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "tool": { "slug": "granite-4-2-30b", "name": "Granite 4.2 30B", "vendor": "IBM", "vendorUrl": "https://www.ibm.com/granite", "kind": "weights", "category": "open-weights", "summary": "Granite 4.2 30B is IBM's open-weight dense reasoning model of 29.3B parameters, post-trained from Granite 4.1 30B Base, with switchable thinking, tool calling and a 131,072-token context, published in BF16, FP8, FP4, GGUF and MLX under Apache 2.0.", "url": "https://www.anchorterminal.com/tools/granite-4-2-30b", "markdownUrl": "https://www.anchorterminal.com/tools/granite-4-2-30b.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/granite-4-2-30b.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/granite-4-2-30b.json", "dns": "granite-4-2-30b.grade.anchorterminal.com", "repo": "https://huggingface.co/ibm-granite/granite-4.2-30b", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "ibm-granite/granite-4.2-30b" }, { "registry": "huggingface", "name": "ibm-granite/granite-4.2-30b-GGUF" }, { "registry": "huggingface", "name": "ibm-granite/granite-4.2-30b-fp8" }, { "registry": "huggingface", "name": "ibm-granite/granite-4.2-30b-mxfp4" }, { "registry": "huggingface", "name": "ibm-granite/granite-4.2-30b-nvfp4" }, { "registry": "huggingface", "name": "ibm-granite/granite-4.2-30b-q4-mlx" }, { "registry": "ollama", "name": "granite4.2:30b" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The BF16 repository and IBM's FP8, MXFP4, NVFP4, GGUF and MLX repositories are not gated (checked 2026-11-10).", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0. Running it yourself costs the hardware, 58.5 GB for the BF16 files, 17.7 GB for IBM's Q4_K_M GGUF or 16.5 GB for its 4-bit MLX build (checked 2026-11-10).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-11-10).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-10" }, "docsUrl": "https://huggingface.co/ibm-granite/granite-4.2-30b", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "dense", "reasoning", "tool-calling", "multilingual", "apache-2.0", "safetensors", "fp8", "fp4", "gguf", "mlx", "signed", "self-hosted" ], "lastRelease": "2026-09-04", "graded": true, "anchor": { "graded": true, "score": 61, "grade": "C", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1518, "categoryRank": 50, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 85, "reach": 90, "risk": 55, "upkeep": 87 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "capability", "name": "Capability", "weight": 35, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending for this listing. Nobody independent has published results for it in at least two areas yet, so its weight is shared across the other four and the total is capped at 61 until they do or our own runs start." }, { "key": "reach", "name": "Reach", "weight": 25, "effectiveWeight": 38.46, "score": 90, "points": 34.62, "reason": "Memory 25, IBM's own 4-bit MLX build granite-4.2-30b-q4-mlx is 16.47 GB, and 16.47 GB × 1.2 = 19.8 GB, which fits 24 GB but not 16 GB. Its Q4_0 GGUF is 16.58 GB and Ollama's library build granite4.2:30b 18 GB, the same band. Runtimes 25, Released versions run the granite architecture in llama.cpp (granite, b12242), vLLM (GraniteForCausalLM in the v0.33.0 registry), SGLang (granite.py at v0.5.23), Transformers (v5.22.2) and Ollama (its own granite4.2 library entry, 30b tag). Builds 15, IBM publishes FP8, MXFP4 and NVFP4 safetensors builds, a GGUF repository with Q4_0 to Q8_0 and BF16 files, and 4-bit, 8-bit and BF16 MLX builds, so quantised builds at two precisions or more. Terms 15, Apache 2.0, an OSI-approved licence, with no use policy or other terms added on the card. Download 10, the Hub API reports gated false for the BF16, FP8, MXFP4, NVFP4, GGUF and MLX repositories, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps one inference provider (DeepInfra, live), short of the two the line needs. 25 + 25 + 15 + 15 + 10 + 0 = 90.", "checked": "2026-11-10" }, { "key": "risk", "name": "Risk", "weight": 20, "effectiveWeight": 30.77, "score": 55, "points": 16.92, "reason": "File safety 15, safetensors only, no .bin, .pt or .pth files (25). Provenance 15, the files sit in the ibm-granite organisation, which IBM's Granite docs and the GitHub README link to (10). Safety evaluation 0, no safety results on the card. Agent guidance 5, General cautions. Licence risk 15, Apache 2.0 has no use policy, field-of-use limit, threshold or change clause, and the card's licence link resolves. Security programme 5, www.ibm.com/.well-known/security.txt names IBM PSIRT, read for the 3B listing on 4 November 2026 (5). 15 + 15 + 0 + 5 + 15 + 5 = 55.", "checked": "2026-11-10" }, { "key": "interface", "name": "Agent interface", "weight": 10, "effectiveWeight": 15.38, "score": 85, "points": 13.08, "reason": "Chat template 20, chat_template.jinja in the repository, with roles, tools, tool responses, the thinking switch and low effort. Tool-calling format 25, the card has tool-calling sections for vLLM and SGLang, declares tools with OpenAI's function schema and names the parser to use, qwen3_coder, which both runtimes ship in the released versions read. Trained tool calling 20, the template loops over every entry in an assistant turn's tool_calls, so it renders several calls in one turn, and the card names tool calling and agentic workflows as what it's best for. Structured output 0, the card doesn't document JSON or JSON Schema output or how to ask for it. Reasoning control 10, the card documents thinking on by default, non-thinking and low-effort modes per request through the template (enable_thinking and low_effort), with the reasoning returned apart from the answer. Context 10, 131,072 tokens natively per the card and config.json. 20 + 25 + 20 + 0 + 10 + 10 = 85.", "checked": "2026-11-10" }, { "key": "upkeep", "name": "Documentation and upkeep", "weight": 10, "effectiveWeight": 15.38, "score": 87, "points": 13.38, "reason": "Model card 17, Intended use (best for), limitations (ethical considerations and limitations), architecture, parameters (30B), context length (128K native) and 12 tested languages are on the card. Training data 20, IBM's disclosure file for the 30B lists the datasets used in pre-training and post-training as machine-readable metadata, and the card describes the three training stages. Last change 15, the last commit to the repository was on 4 September 2026, 67 days before this check. Responsiveness 20, Of the 4 discussions that aren't pull requests (28 August to 3 November 2026), 3 have a reply from an ibm-granite member. Version policy 5, Granite 4.1 30B stays in its own repository and 4.2 came out in new ones. File health 10, Config, template and card agree on the architecture, the 131,072-token context and the thinking switch. 17 + 20 + 15 + 20 + 5 + 10 = 87.", "checked": "2026-11-10" } ], "assessment": { "date": "2026-11-10", "basis": "public evidence", "confidence": "low", "notes": { "capability": "Pending for this listing. Independent results were found in 0 areas (none), and Capability needs 2. Its weight is shared across the other four categories and the total is capped at 61 until there are more, or our own runs start.", "interface": "Chat template 20, chat_template.jinja in the repository, with roles, tools, tool responses, the thinking switch and low effort. Tool-calling format 25, the card has tool-calling sections for vLLM and SGLang, declares tools with OpenAI's function schema and names the parser to use, qwen3_coder, which both runtimes ship in the released versions read. Trained tool calling 20, the template loops over every entry in an assistant turn's tool_calls, so it renders several calls in one turn, and the card names tool calling and agentic workflows as what it's best for. Structured output 0, the card doesn't document JSON or JSON Schema output or how to ask for it. Reasoning control 10, the card documents thinking on by default, non-thinking and low-effort modes per request through the template (enable_thinking and low_effort), with the reasoning returned apart from the answer. Context 10, 131,072 tokens natively per the card and config.json. 20 + 25 + 20 + 0 + 10 + 10 = 85.", "reach": "Memory 25, IBM's own 4-bit MLX build granite-4.2-30b-q4-mlx is 16.47 GB, and 16.47 GB × 1.2 = 19.8 GB, which fits 24 GB but not 16 GB. Its Q4_0 GGUF is 16.58 GB and Ollama's library build granite4.2:30b 18 GB, the same band. Runtimes 25, Released versions run the granite architecture in llama.cpp (granite, b12242), vLLM (GraniteForCausalLM in the v0.33.0 registry), SGLang (granite.py at v0.5.23), Transformers (v5.22.2) and Ollama (its own granite4.2 library entry, 30b tag). Builds 15, IBM publishes FP8, MXFP4 and NVFP4 safetensors builds, a GGUF repository with Q4_0 to Q8_0 and BF16 files, and 4-bit, 8-bit and BF16 MLX builds, so quantised builds at two precisions or more. Terms 15, Apache 2.0, an OSI-approved licence, with no use policy or other terms added on the card. Download 10, the Hub API reports gated false for the BF16, FP8, MXFP4, NVFP4, GGUF and MLX repositories, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps one inference provider (DeepInfra, live), short of the two the line needs. 25 + 25 + 15 + 15 + 10 + 0 = 90.", "risk": "File safety 15, safetensors only, no .bin, .pt or .pth files (25). Provenance 15, the files sit in the ibm-granite organisation, which IBM's Granite docs and the GitHub README link to (10). Safety evaluation 0, no safety results on the card. Agent guidance 5, General cautions. Licence risk 15, Apache 2.0 has no use policy, field-of-use limit, threshold or change clause, and the card's licence link resolves. Security programme 5, www.ibm.com/.well-known/security.txt names IBM PSIRT, read for the 3B listing on 4 November 2026 (5). 15 + 15 + 0 + 5 + 15 + 5 = 55.", "upkeep": "Model card 17, Intended use (best for), limitations (ethical considerations and limitations), architecture, parameters (30B), context length (128K native) and 12 tested languages are on the card. Training data 20, IBM's disclosure file for the 30B lists the datasets used in pre-training and post-training as machine-readable metadata, and the card describes the three training stages. Last change 15, the last commit to the repository was on 4 September 2026, 67 days before this check. Responsiveness 20, Of the 4 discussions that aren't pull requests (28 August to 3 November 2026), 3 have a reply from an ibm-granite member. Version policy 5, Granite 4.1 30B stays in its own repository and 4.2 came out in new ones. File health 10, Config, template and card agree on the architecture, the 131,072-token context and the thinking switch. 17 + 20 + 15 + 20 + 5 + 10 = 87." }, "sources": [ { "what": "model card", "url": "https://huggingface.co/ibm-granite/granite-4.2-30b", "seen": "2026-11-10" }, { "what": "gating, dates, parameter count, downloads, likes, file list and hashes", "url": "https://huggingface.co/api/models/ibm-granite/granite-4.2-30b?blobs=true", "seen": "2026-11-10" }, { "what": "inference providers, DeepInfra", "url": "https://huggingface.co/api/models/ibm-granite/granite-4.2-30b?expand[]=inferenceProviderMapping", "seen": "2026-11-10" }, { "what": "commit history", "url": "https://huggingface.co/api/models/ibm-granite/granite-4.2-30b/commits/main", "seen": "2026-11-10" }, { "what": "architecture and context length", "url": "https://huggingface.co/ibm-granite/granite-4.2-30b/raw/main/config.json", "seen": "2026-11-10" }, { "what": "chat template", "url": "https://huggingface.co/ibm-granite/granite-4.2-30b/raw/main/chat_template.jinja", "seen": "2026-11-10" }, { "what": "the vLLM parser plugin in the repository", "url": "https://huggingface.co/ibm-granite/granite-4.2-30b/raw/main/granite_thinking_parser.py", "seen": "2026-11-10" }, { "what": "discussions, replies counted by script from authors, dates and member flags", "url": "https://huggingface.co/api/models/ibm-granite/granite-4.2-30b/discussions", "seen": "2026-11-10" }, { "what": "IBM's builds for Granite 4.2 and their sizes", "url": "https://huggingface.co/api/models?author=ibm-granite\u0026search=granite-4.2", "seen": "2026-11-10" }, { "what": "IBM's GGUF files and sizes", "url": "https://huggingface.co/api/models/ibm-granite/granite-4.2-30b-GGUF?blobs=true", "seen": "2026-11-10" }, { "what": "IBM's 4-bit MLX build", "url": "https://huggingface.co/api/models/ibm-granite/granite-4.2-30b-q4-mlx?blobs=true", "seen": "2026-11-10" }, { "what": "IBM's disclosure file for this size", "url": "https://raw.githubusercontent.com/ibm-granite/granite-4.2-language-models/main/disclosures/granite_4.2_30b_disclosure.json", "seen": "2026-11-10" }, { "what": "Ollama's library tags for granite4.2", "url": "https://ollama.com/library/granite4.2/tags", "seen": "2026-11-10" }, { "what": "LM Studio's GGUF of it on the Hub", "url": "https://huggingface.co/api/models/lmstudio-community/granite-4.2-30b-GGUF?blobs=true", "seen": "2026-11-10" }, { "what": "vLLM v0.33.0 registry, GraniteForCausalLM", "url": "https://raw.githubusercontent.com/vllm-project/vllm/v0.33.0/vllm/model_executor/models/registry.py", "seen": "2026-11-10" }, { "what": "SGLang v0.5.23 granite.py", "url": "https://raw.githubusercontent.com/sgl-project/sglang/v0.5.23/python/sglang/srt/models/granite.py", "seen": "2026-11-10" }, { "what": "llama.cpp b12242, the Granite conversion code (shallow clone)", "url": "https://raw.githubusercontent.com/ggml-org/llama.cpp/b12242/conversion/granite.py", "seen": "2026-11-10" }, { "what": "IBM's Granite 4.2 docs page, read for the 3B listing", "url": "https://www.ibm.com/granite/docs/models/granite4-2", "seen": "2026-11-10" }, { "what": "IBM's security.txt, read for the 3B listing", "url": "https://www.ibm.com/.well-known/security.txt", "seen": "2026-11-10" } ], "openQuestions": [ "Hosted is 0 with one provider mapped on Hugging Face. OpenRouter listed granite-4.2-8b on 4 November per the 3B listing, which may count as a second for the 8B", "File health is 10 although one discussion from 28 August has no reply from IBM. If that discussion reports a broken file, the line is 5", "Capability is pending because no independent results were looked up for this size on the day. The 3B has a Capability score, so results for the family exist", "The disclosure file's dataset entries weren't counted for this size, as they were for the 3B", "unchecked on 10 November: IBM's docs page, blog, GitHub README and security.txt, read for the 3B listing on 21 October and 4 November, and the Granite 4.1 30B card for a dated note" ] }, "negative": 0, "verdict": "IBM's largest reasoning cousin, with the same strengths as the 3B. It runs in every runtime we count from IBM's own builds on a 24 GB card, is signed, plain Apache 2.0, and comes with a disclosure of its training data. No safety results are published and structured output isn't documented.", "bestFor": "Agents that want a documented, signed, Apache 2.0 reasoning model with tool calling on a 24 GB card", "strengths": [ "Runs in llama.cpp, Ollama, vLLM, SGLang and Transformers from IBM's own FP8, FP4, GGUF and MLX builds", "Plain Apache 2.0, ungated, signed with sigstore", "The card documents the tool-calling format, the parser to use and three thinking modes", "IBM publishes a machine-readable disclosure of the training datasets", "IBM answers most questions on the repository" ], "weaknesses": [ "No safety results published for it", "Structured output isn't documented", "The card's vLLM command still loads a Python plugin from the repository, which released vLLM no longer needs", "No knowledge cut-off on the card", "One inference provider, so an agent without the hardware has little choice" ], "agentNotes": [ "Start it with `ollama run granite4.2:30b`, or `llama-server -hf ibm-granite/granite-4.2-30b-GGUF:Q4_K_M --jinja`", "With vLLM 0.32.0 or later leave out `--reasoning-parser-plugin`, since the parser is built in, and use `--tool-call-parser qwen3_coder`", "Thinking is on by default. Pass `enable_thinking` false to turn it off or `low_effort` true for short reasoning", "The context is 131,072 tokens. The card's 512K extension isn't documented", "Validate JSON output yourself, since structured output isn't documented", "IBM recommends Granite Guardian beside it to flag risky inputs and outputs" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61 } ], "editorialScores": { "interface": 85, "reach": 90, "risk": 55, "upkeep": 87 }, "provenanceScore": 88, "checked": { "categories": { "interface": "2026-11-10", "reach": "2026-11-10", "risk": "2026-11-10", "upkeep": "2026-11-10" }, "last": "2026-11-10", "oldest": "2026-11-10", "stale": false, "staleAfterDays": 90 }, "scoreHistory": [ { "date": "2026-11-10", "grade": "C", "kind": "listed", "method": "0.7", "score": 61 } ] }, "connect": { "install": "ollama run granite4.2:30b\n# or, with llama.cpp and IBM's own GGUF:\nllama-server -hf ibm-granite/granite-4.2-30b-GGUF:Q4_K_M --jinja\n# or, with vLLM 0.32.0 or later:\nvllm serve ibm-granite/granite-4.2-30b --max-model-len 131072 \\\n --reasoning-parser granite_thinking_parser \\\n --tool-call-parser qwen3_coder --enable-auto-tool-choice", "http": "curl http://localhost:11434/api/chat \\\n -d '{\"model\": \"granite4.2:30b\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}]}'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/granite-4-2-30b" }, "sameCompany": [ "granite-embedding-small-english-r2", "granite-guardian", "ibm-watson-stt", "granite-switch", "granite-4-2-3b", "granite-4-2-8b" ], "weights": { "trainedBy": "IBM", "builtOn": "ibm-granite/granite-4.1-30b-base (IBM's own base checkpoint, post-trained; named on the card and in its metadata)", "params": "29.3B", "context": 131072, "goodFor": "IBM's largest dense reasoning model for tool calling, coding and multilingual chat, with thinking that is on, off or short per request, on a 24 GB card at 4 bits.", "runtimes": [ "llama.cpp", "Ollama", "vLLM", "SGLang", "Transformers" ], "builds": [ { "name": "granite-4.2-30b-nvfp4", "url": "https://huggingface.co/ibm-granite/granite-4.2-30b-nvfp4", "who": "publisher", "precision": "nvfp4", "sizeGB": 17.65, "memoryGB": 24, "format": "safetensors", "runsOn": [ "vLLM" ] }, { "name": "granite-4.2-30b-mxfp4", "url": "https://huggingface.co/ibm-granite/granite-4.2-30b-mxfp4", "who": "publisher", "precision": "mxfp4", "sizeGB": 16.76, "memoryGB": 24, "format": "safetensors", "runsOn": [ "vLLM" ] }, { "name": "granite-4.2-30b-Q4_K_M", "url": "https://huggingface.co/ibm-granite/granite-4.2-30b-GGUF", "who": "publisher", "precision": "q4_k_m", "sizeGB": 17.72, "memoryGB": 24, "format": "gguf", "runsOn": [ "llama.cpp" ], "note": "IBM's GGUF repository also holds Q4_0 (16.58 GB), Q6_K and BF16 files among others" }, { "name": "granite-4.2-30b-q4-mlx", "url": "https://huggingface.co/ibm-granite/granite-4.2-30b-q4-mlx", "who": "publisher", "precision": "q4", "sizeGB": 16.47, "memoryGB": 24, "format": "mlx", "runsOn": [ "mlx-lm" ], "note": "The smallest build at 4-bit or better. IBM also publishes q8-mlx (31.11 GB) and bf16-mlx" }, { "name": "ollama granite4.2:30b", "url": "https://ollama.com/library/granite4.2:30b", "who": "ollama", "precision": "q4_k_m", "sizeGB": 18, "memoryGB": 24, "format": "ollama", "runsOn": [ "Ollama" ], "note": "Ollama's library build, size as its tags page shows it on 10 November 2026" }, { "name": "granite-4.2-30b-fp8", "url": "https://huggingface.co/ibm-granite/granite-4.2-30b-fp8", "who": "publisher", "precision": "fp8", "sizeGB": 30.11, "memoryGB": 48, "format": "safetensors", "runsOn": [ "vLLM" ] }, { "name": "granite-4.2-30b-Q8_0", "url": "https://huggingface.co/ibm-granite/granite-4.2-30b-GGUF", "who": "publisher", "precision": "q8_0", "sizeGB": 31.11, "memoryGB": 48, "format": "gguf", "runsOn": [ "llama.cpp" ] }, { "name": "granite-4.2-30b", "url": "https://huggingface.co/ibm-granite/granite-4.2-30b", "who": "publisher", "precision": "bf16", "sizeGB": 58.55, "memoryGB": 96, "format": "safetensors", "runsOn": [ "vLLM", "SGLang", "Transformers" ] } ], "run": "ollama run granite4.2:30b", "runBuild": "ollama granite4.2:30b", "checked": "2026-11-10", "minMemoryGB": 24 }, "family": { "lab": "IBM (Granite)", "family": "Granite 4 (4.0, 4.1, 4.2)", "url": "https://www.anchorterminal.com/open-weights/#ibm", "others": [ { "name": "granite-4.2-3b", "url": "https://huggingface.co/ibm-granite/granite-4.2-3b", "params": "3B (Hub safetensors count 3.66B)", "listing": "https://www.anchorterminal.com/tools/granite-4-2-3b" }, { "name": "granite-4.2-8b", "url": "https://huggingface.co/ibm-granite/granite-4.2-8b", "params": "8B (Hub safetensors count 8.79B)", "listing": "https://www.anchorterminal.com/tools/granite-4-2-8b" }, { "name": "granite-4.1-8b-base", "url": "https://huggingface.co/ibm-granite/granite-4.1-8b-base", "params": "8B (Hub safetensors count 8.38B)" }, { "name": "granite-4.1-8b", "url": "https://huggingface.co/ibm-granite/granite-4.1-8b", "params": "8B (Hub safetensors count 8.79B)" }, { "name": "granite-4.1-3b-base", "url": "https://huggingface.co/ibm-granite/granite-4.1-3b-base", "params": "3B (Hub safetensors count 3.40B)" }, { "name": "granite-4.1-3b", "url": "https://huggingface.co/ibm-granite/granite-4.1-3b", "params": "3B (Hub safetensors count 3.40B)" }, { "name": "granite-4.1-30b-base", "url": "https://huggingface.co/ibm-granite/granite-4.1-30b-base", "params": "30B (Hub safetensors count 28.87B)" }, { "name": "granite-4.1-30b", "url": "https://huggingface.co/ibm-granite/granite-4.1-30b", "params": "30B (Hub safetensors count 28.87B)" }, { "name": "granite-4.0-h-350m-base", "url": "https://huggingface.co/ibm-granite/granite-4.0-h-350m-base", "params": "350M (Hub safetensors count 340M)" }, { "name": "granite-4.0-h-350m", "url": "https://huggingface.co/ibm-granite/granite-4.0-h-350m", "params": "350M (Hub safetensors count 340M)" }, { "name": "granite-4.0-h-1b-base", "url": "https://huggingface.co/ibm-granite/granite-4.0-h-1b-base", "params": "1B (Hub safetensors count 1.46B)" }, { "name": "granite-4.0-h-1b", "url": "https://huggingface.co/ibm-granite/granite-4.0-h-1b", "params": "1B (Hub safetensors count 1.46B)" }, { "name": "granite-4.0-350m-base", "url": "https://huggingface.co/ibm-granite/granite-4.0-350m-base", "params": "350M (Hub safetensors count 352M)" }, { "name": "granite-4.0-350m", "url": "https://huggingface.co/ibm-granite/granite-4.0-350m", "params": "350M (Hub safetensors count 352M)" }, { "name": "granite-4.0-1b-base", "url": "https://huggingface.co/ibm-granite/granite-4.0-1b-base", "params": "1B (Hub safetensors count 1.63B)" }, { "name": "granite-4.0-1b", "url": "https://huggingface.co/ibm-granite/granite-4.0-1b", "params": "1B (Hub safetensors count 1.63B)" }, { "name": "granite-4.0-micro-base", "url": "https://huggingface.co/ibm-granite/granite-4.0-micro-base", "params": "3.40B (Hub safetensors count; the name states none)" }, { "name": "granite-4.0-micro", "url": "https://huggingface.co/ibm-granite/granite-4.0-micro", "params": "3.40B (Hub safetensors count; the name states none)" }, { "name": "granite-4.0-h-tiny-base", "url": "https://huggingface.co/ibm-granite/granite-4.0-h-tiny-base", "params": "6.94B (Hub safetensors count; the name states none)" }, { "name": "granite-4.0-h-tiny", "url": "https://huggingface.co/ibm-granite/granite-4.0-h-tiny", "params": "6.94B (Hub safetensors count; the name states none)" }, { "name": "granite-4.0-h-small-base", "url": "https://huggingface.co/ibm-granite/granite-4.0-h-small-base", "params": "32.21B (Hub safetensors count; the name states none)" }, { "name": "granite-4.0-h-small", "url": "https://huggingface.co/ibm-granite/granite-4.0-h-small", "params": "32.21B (Hub safetensors count; the name states none)" }, { "name": "granite-4.0-h-micro-base", "url": "https://huggingface.co/ibm-granite/granite-4.0-h-micro-base", "params": "3.19B (Hub safetensors count; the name states none)" }, { "name": "granite-4.0-h-micro", "url": "https://huggingface.co/ibm-granite/granite-4.0-h-micro", "params": "3.19B (Hub safetensors count; the name states none)" }, { "name": "granite-4.0-tiny-preview", "url": "https://huggingface.co/ibm-granite/granite-4.0-tiny-preview", "params": "6.67B (Hub safetensors count; the name states none)" }, { "name": "granite-4.0-tiny-base-preview", "url": "https://huggingface.co/ibm-granite/granite-4.0-tiny-base-preview", "params": "6.67B (Hub safetensors count; the name states none)" } ], "olderCount": 64 }, "notable": [ "36,918 downloads in the last 30 days and 142 likes on Hugging Face on 10 November 2026, and 249,597 for IBM's GGUF repository (https://huggingface.co/api/models/ibm-granite/granite-4.2-30b)", "The card gives 62.0 on τ³-bench (average), 61.39 on BFCL v4 and 89.17 on AIME25 for this size, against 45.78 on τ³-bench for the 3B. These are IBM's numbers, not our measurement (https://huggingface.co/ibm-granite/granite-4.2-30b)", "IBM publishes a machine-readable disclosure of the training datasets for this size, dated 3 September 2026, with a release date of 25 August 2026 (https://github.com/ibm-granite/granite-4.2-language-models/tree/main/disclosures)", "The repository carries model.sig, a sigstore signature over the files (https://huggingface.co/ibm-granite/granite-4.2-30b)", "The card still says to load the repository's granite_thinking_parser.py as a vLLM plugin, while released vLLM and SGLang register a granite_thinking_parser of their own (https://huggingface.co/ibm-granite/granite-4.2-30b)", "DeepInfra serves it, the one inference provider Hugging Face maps (https://huggingface.co/api/models/ibm-granite/granite-4.2-30b?expand[]=inferenceProviderMapping)" ], "area": "models", "details": [ { "label": "Surface graded", "value": "The open weights at huggingface.co/ibm-granite/granite-4.2-30b with IBM's FP8, MXFP4, NVFP4, GGUF and MLX builds, read from the model card, the files and their metadata, the chat template, IBM's disclosure file for this size, Ollama's library and the runtimes' own code at their latest releases on 10 November 2026. IBM's docs, blog, licence and security.txt were read for the 3B listing on 21 October and 4 November. Nothing was downloaded or run" }, { "label": "Model", "value": "A dense decoder-only transformer (GraniteForCausalLM), 64 layers, hidden size 4,096, 32 attention heads with 8 KV heads, SwiGLU (32,768), RoPE with theta 50,000,000 and separate input and output embeddings. 29,276,770,304 parameters per the Hub; the card says 30B. Post-trained from IBM's own granite-4.1-30b-base" }, { "label": "Languages", "value": "English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch and Chinese tested, per the card" }, { "label": "Context", "value": "131,072 tokens per the card (natively 128K) and config.json (max_position_embeddings 131072). The card also names a long-context extension to 512K, without saying how to turn it on" }, { "label": "Tools and reasoning", "value": "Tools are declared with OpenAI's function schema and listed in a system turn inside \u003ctools\u003e. Calls come back as \u003ctool_call\u003e\u003cfunction=name\u003e\u003cparameter=key\u003evalue\u003c/parameter\u003e\u003c/function\u003e\u003c/tool_call\u003e, several per turn, and the card names the qwen3_coder parser for vLLM and SGLang. Thinking is on by default inside \u003cthink\u003e, enable_thinking false turns it off and low_effort true shortens it, and SGLang returns it in reasoning_content" }, { "label": "Files", "value": "Eleven safetensors shards, 58.55 GB in BF16, a chat_template.jinja, granite_thinking_parser.py (a vLLM reasoning-parser plugin) and model.sig, a sigstore signature. No pickle files. Hugging Face lists a SHA-256 for every shard" }, { "label": "Licence", "value": "Apache 2.0, per the card, the metadata and the GitHub repository's LICENSE. No LICENSE file in the Hugging Face repository. The base, granite-4.1-30b-base, is IBM's own under Apache 2.0" }, { "label": "Runtimes", "value": "Transformers (granite), vLLM (GraniteForCausalLM in the 0.33.0 registry), SGLang (granite.py at 0.5.23), llama.cpp (granite, with IBM's GGUF) and Ollama's library (granite4.2:30b). LM Studio's organisation on the Hub also publishes a GGUF of it" }, { "label": "Hardware", "value": "No memory figure on the card. The BF16 files are 58.5 GB, IBM's FP8 build 30.1 GB, its MXFP4 and NVFP4 builds 16.8 and 17.6 GB, its Q4_K_M GGUF 17.7 GB and its 4-bit MLX build 16.5 GB" }, { "label": "Training data", "value": "IBM's disclosure file for this size lists the datasets used in pre-training and post-training with their metadata, released as a governance record on 3 September 2026. The card describes the three training stages, pre-training, supervised fine-tuning and reinforcement learning" } ], "provenance": { "legalEntity": "International Business Machines Corporation (per IBM's naming guidance, as read for granite-guardian)", "domain": "ibm.com", "domainRegistered": "1986-03-19", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/ibm-granite/granite-4.2-30b/commits/main", "securityTxt": "valid", "checked": "2026-11-10", "notes": [ "IBM's Granite docs page for 4.2 links the ibm-granite collection on Hugging Face and the GitHub repository, and the docs site says it is no longer updated. The domain date is carried from the granite-guardian check.", "The ibm-granite organisation (209 members) isn't verified on the Hub, which the calibration doesn't require.", "Nothing is hosted for this listing, so the Apache 2.0 licence stands in for terms of service and no privacy policy is scored.", "The changelog is the Hugging Face commit history, 15 commits from 7 August to 20 October 2026, most titled only \"granite-4.2\".", "www.ibm.com/.well-known/security.txt is present with PSIRT contacts and expires on 21 November 2026.", "Released on 25 August 2026 by the card and IBM's blog, which firstReleased uses. The repository and its weight files date from 7 August 2026, the date BATCH.md and the IBM family page used before 21 October." ], "score": 88, "checks": [ { "check": "Legal entity named", "value": "International Business Machines Corporation (per IBM's naming guidance, as read for granite-guardian)", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "ibm.com, registered 1986-03-19 (40 years)", "points": 15, "max": 15, "state": "ok" }, { "check": "Endpoint on the vendor's domain", "value": "no hosted endpoint", "points": 0, "max": 0, "state": "na" }, { "check": "Terms of service", "value": "nothing hosted, so the Apache-2.0 licence stands in", "points": 10, "max": 10, "state": "ok" }, { "check": "Privacy policy", "value": "nothing hosted, not scored", "points": 0, "max": 0, "state": "na" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "valid", "points": 10, "max": 10, "state": "ok" }, { "check": "People named", "value": "5 named with their role, none with a public profile", "points": 7, "max": 10, "state": "part" }, { "check": "Support route", "value": "help pages, a community", "points": 5, "max": 5, "state": "ok" } ] }, "humans": { "slug": "granite-4-2-30b", "checked": "2026-11-10", "company": "IBM", "people": [ { "name": "Charles Ranlett Flint", "role": "Co-founder, IBM (as Computing-Tabulating-Recording Company)", "founder": true, "bio": "Charles Ranlett Flint was a financier who in 1911 amalgamated four companies to form the Computing-Tabulating-Recording Company, renamed International Business Machines in 1924. His financial dealings earned him the nickname \"Father of Trusts\".", "bioSources": [ "https://en.wikipedia.org/wiki/Charles_Ranlett_Flint", "https://en.wikipedia.org/wiki/IBM" ], "page": "/people/charles-ranlett-flint/" }, { "name": "Herman Hollerith", "role": "Co-founder, IBM (as Computing-Tabulating-Recording Company)", "founder": true, "bio": "Herman Hollerith was a statistician and inventor who developed the electromechanical punched-card tabulating machine. The company he founded was one of those amalgamated in 1911 into the Computing-Tabulating-Recording Company, which was renamed IBM in 1924.", "bioSources": [ "https://en.wikipedia.org/wiki/Herman_Hollerith", "https://en.wikipedia.org/wiki/IBM" ], "page": "/people/herman-hollerith/" }, { "name": "George Winthrop Fairchild", "role": "Co-founder, IBM (as Computing-Tabulating-Recording Company)", "founder": true, "bio": "George Winthrop Fairchild was an investor in the time-recording industry who formed the International Time Recording Company in 1900. He became president of the Computing-Tabulating-Recording Company at its formation in 1911 and was its chairman, and IBM's after the 1924 renaming, until his death that year.", "bioSources": [ "https://en.wikipedia.org/wiki/George_W._Fairchild", "https://en.wikipedia.org/wiki/IBM" ], "page": "/people/george-winthrop-fairchild/" }, { "name": "Arvind Krishna", "role": "Chairman, President and Chief Executive Officer", "photo": "/assets/img/people/ibm-arvind-krishna.webp", "photoSource": "https://newsroom.ibm.com/Arvind-Krishna", "bio": "Arvind Krishna is chairman, president and chief executive of IBM. Over some 30 years at the company he headed IBM Research, ran its Cloud and Cognitive Software unit and drove the $34 billion purchase of Red Hat. He holds an undergraduate degree from IIT Kanpur and a PhD from the University of Illinois at Urbana-Champaign.", "bioSources": [ "https://newsroom.ibm.com/Arvind-Krishna" ], "page": "/people/arvind-krishna/" }, { "name": "Jay Gambetta", "role": "Director of IBM Research", "photo": "/assets/img/people/ibm-jay-gambetta.webp", "photoSource": "https://newsroom.ibm.com/executive-bios", "bio": "Jay Gambetta is IBM's Director of Research and an IBM Fellow, leading the lab whose work spans AI, semiconductors and quantum computing. He earlier ran IBM Quantum as vice president and led the development of Qiskit, the open-source quantum software kit. A physicist, he holds a PhD from Griffith University in Australia.", "bioSources": [ "https://newsroom.ibm.com/Jay-Gambetta" ], "page": "/people/jay-gambetta/" } ], "peopleNote": "IBM is a listed company whose founders, per Wikipedia, are those of its 1911 predecessor, the Computing-Tabulating-Recording Company. IBM's senior leadership page, read on 28 October 2026, names Arvind Krishna as Chairman, President and Chief Executive Officer and Jay Gambetta as Director of IBM Research, the lab that announces and publishes the Granite models (https://research.ibm.com/blog/introducing-granite-4-2). IBM names no chief technology officer there, and the Granite pages name no single product lead. The paper authors on two listings (Parul Awasthy on granite-embedding-small-english-r2, Inkit Padhi on granite-guardian) stay as they are.", "companySocial": { "linkedin": "https://www.linkedin.com/company/ibm", "x": "https://x.com/ibm", "github": "https://github.com/ibm-granite" }, "support": { "urls": [ "https://huggingface.co/ibm-granite/granite-4.2-30b/discussions", "https://github.com/ibm-granite/granite-4.2-language-models/issues" ], "community": [ { "label": "Model community discussions", "url": "https://huggingface.co/ibm-granite/granite-4.2-30b/discussions", "kind": "link" } ] }, "sources": [ "https://huggingface.co/ibm-granite/granite-4.2-3b", "https://huggingface.co/ibm-granite/granite-4.2-3b/discussions", "https://en.wikipedia.org/wiki/IBM", "https://en.wikipedia.org/wiki/Charles_Ranlett_Flint", "https://en.wikipedia.org/wiki/Herman_Hollerith", "https://en.wikipedia.org/wiki/George_W._Fairchild", "https://www.ibm.com/granite", "https://www.ibm.com/us-en" ], "ownership": { "status": "public", "exchange": "NYSE", "ticker": "IBM", "checked": "2026-10-28", "sources": [ "https://en.wikipedia.org/wiki/IBM", "https://www.ibm.com/investor" ] } }, "pageJsonUrl": "https://www.anchorterminal.com/tools/granite-4-2-30b.json" } }