Granite 4.2 30B is IBM's flagship reasoning language model with support for thinking modes, tool calling, and text generation.
Granite 4.2 3B is a compact reasoning language model from IBM with support for thinking modes, tool calling, and text generation.
Granite 4.2 8B is a reasoning language model from IBM with support for thinking modes, tool calling, and text generation.
Granite 4.1 30B is a language model from IBM for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
Granite 4.1 3B is a language model from IBM for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
Granite 4.1 8B is a language model from IBM for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
Granite 4.0 Micro is a language model from IBM for chat, writing, analysis, and general-purpose automation. It is a smaller-footprint option suited to tighter latency or deployment budgets.
Granite 4.0 Small is a language model from IBM for chat, writing, analysis, and general-purpose automation. It is a smaller-footprint option suited to tighter latency or deployment budgets.
Granite 4.0 Tiny is a language model from IBM for chat, writing, analysis, and general-purpose automation. It is a smaller-footprint option suited to tighter latency or deployment budgets.
Granite 4.0 Tiny Preview is a language model from IBM for chat, writing, analysis, and general-purpose automation. This entry tracks a preview release and capabilities may change before general availability.
Granite 3.3 2B Instruct is a language model from IBM for chat, writing, analysis, and general-purpose automation.
Granite 3.3 8B Instruct is a language model from IBM for chat, writing, analysis, and general-purpose automation.
Granite 4.0 H Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. It is a smaller-footprint option suited to tighter latency or deployment budgets.
Granite 20B Code Instruct 8K is a coding model from IBM for code generation, edits, and software tasks.
Granite 3.0 1B A400M Instruct is a language model from IBM for chat, writing, analysis, and general-purpose automation.
Granite 3.0 2B Instruct is a language model from IBM for chat, writing, analysis, and general-purpose automation.
Granite 3.0 3B A800M Instruct is a language model from IBM for chat, writing, analysis, and general-purpose automation.
Granite 3.0 8B Instruct is a language model from IBM for chat, writing, analysis, and general-purpose automation.
Granite 3.1 1B A400M Instruct is a language model from IBM for chat, writing, analysis, and general-purpose automation.
Granite 3.1 2B Instruct is a language model from IBM for chat, writing, analysis, and general-purpose automation.
Granite 3.1 3B A800M Instruct is a language model from IBM for chat, writing, analysis, and general-purpose automation.
Granite 3.1 8B Instruct is a language model from IBM for chat, writing, analysis, and general-purpose automation.
Granite 3.2 2B Instruct is a language model from IBM for chat, writing, analysis, and general-purpose automation.
Granite 3.2 8B Instruct is a language model from IBM for chat, writing, analysis, and general-purpose automation.
Granite 3.2 8B Instruct Preview is a language model from IBM for chat, writing, analysis, and general-purpose automation. This entry tracks a preview release and capabilities may change before general availability.
Granite 34B Code Instruct 8B is a coding model from IBM for code generation, edits, and software tasks.
Granite 3B Code Instruct 128K is a coding model from IBM for code generation, edits, and software tasks.
Granite 3B Code Instruct 2K is a coding model from IBM for code generation, edits, and software tasks.
Granite 8B Code Instruct 128K is a coding model from IBM for code generation, edits, and software tasks.
Granite 8B Code Instruct 4K is a coding model from IBM for code generation, edits, and software tasks.
Granite Embedding 107M Multilingual is an embedding model from IBM for vector search and semantic retrieval workflows. It is aimed at multilingual retrieval and semantic similarity tasks.
Granite Embedding 125M English is an embedding model from IBM for vector search and semantic retrieval workflows. It is aimed at English-language retrieval, clustering, and semantic search.
Granite Embedding 278M Multilingual is an embedding model from IBM for vector search and semantic retrieval workflows. It is aimed at multilingual retrieval and semantic similarity tasks.
Granite Embedding 30M English is an embedding model from IBM for vector search and semantic retrieval workflows. It is aimed at English-language retrieval, clustering, and semantic search.
Granite Embedding English R2 is an embedding model from IBM for vector search and semantic retrieval workflows. It is aimed at English-language retrieval, clustering, and semantic search.
Granite Embedding Reranker English R2 is a reranking model from IBM for improving retrieval quality by rescoring candidate results against a query. Use it to rescore retrieved passages, products, or documents before final ranking or generation.
Granite Embedding Small English R2 is an embedding model from IBM for vector search and semantic retrieval workflows. It is aimed at English-language retrieval, clustering, and semantic search.
Granite Guardian 3.0 2B is a safety model from IBM for moderation, prompt filtering, and policy enforcement. It is suited to input filtering, safety checks, and policy enforcement in LLM applications.
Granite Guardian 3.0 8B is a safety model from IBM for moderation, prompt filtering, and policy enforcement. It is suited to input filtering, safety checks, and policy enforcement in LLM applications.
Granite Guardian 3.1 2B is a safety model from IBM for moderation, prompt filtering, and policy enforcement. It is suited to input filtering, safety checks, and policy enforcement in LLM applications.
Granite Guardian 3.1 8B is a safety model from IBM for moderation, prompt filtering, and policy enforcement. It is suited to input filtering, safety checks, and policy enforcement in LLM applications.
Granite Guardian 3.2 5B is a safety model from IBM for moderation, prompt filtering, and policy enforcement. It is suited to input filtering, safety checks, and policy enforcement in LLM applications.
Granite Guardian 3.3 8B is a safety model from IBM for moderation, prompt filtering, and policy enforcement. It is suited to input filtering, safety checks, and policy enforcement in LLM applications.
Granite Speech 3.2 8B is a language model from IBM for chat, writing, analysis, and general-purpose automation.
Granite Speech 3.3 2B is a language model from IBM for chat, writing, analysis, and general-purpose automation.
Granite Speech 3.3 8B is a language model from IBM for chat, writing, analysis, and general-purpose automation.
Granite Vision 3.1 2B Preview is a multimodal model from IBM that can work across text and visual inputs. This entry tracks a preview release and capabilities may change before general availability.
Granite Vision 3.2 2B is a multimodal model from IBM that can work across text and visual inputs.
Granite Vision 3.3 2B is a multimodal model from IBM that can work across text and visual inputs.
Granite Vision 3.3 2B Embedding is an embedding model from IBM for vector search and semantic retrieval workflows. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.