Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
IBM Granite · Ollama
Search for models on Ollama.
  • granite4.1

    IBM Granite Models are a family of enterprise-ready, open foundation models that support multilingual capabilities, coding, retrieval-augmented generation (RAG), tool use, and structured JSON output. Released under Apache 2.0 license.

    tools 3b 8b 30b

    462.1K  Pulls 48  Tags Updated  4 months ago

  • granite4.2

    IBM Granite Models are a family of enterprise-ready, open foundation models that support multilingual capabilities, coding, retrieval-augmented generation (RAG), tool use, thinking and structured JSON output. Released under Apache 2.0 license.

    3b 8b 30b

    78.6K  Pulls 49  Tags Updated  3 weeks ago

  • granite3.1-moe

    The IBM Granite 1B and 3B models are long-context mixture of experts (MoE) Granite models from IBM designed for low latency usage.

    tools 1b 3b

    3M  Pulls 33  Tags Updated  1 year ago

  • granite3.3

    IBM Granite 2B and 8B models are 128K context length language models that have been fine-tuned for improved reasoning and instruction-following capabilities.

    tools 2b 8b

    1.1M  Pulls 3  Tags Updated  1 year ago

  • granite3.1-dense

    The IBM Granite 2B and 8B models are text-only dense LLMs trained on over 12 trillion tokens of data, demonstrated significant improvements over their predecessors in performance and speed in IBM’s initial testing.

    tools 2b 8b

    1M  Pulls 33  Tags Updated  1 year ago

  • granite3-dense

    The IBM Granite 2B and 8B models are designed to support tool-based use cases and support for retrieval augmented generation (RAG), streamlining code generation, translation and bug fixing.

    tools 2b 8b

    1M  Pulls 33  Tags Updated  1 year ago

  • granite3-moe

    The IBM Granite 1B and 3B models are the first mixture of experts (MoE) Granite models from IBM designed for low latency usage.

    tools 1b 3b

    963.6K  Pulls 33  Tags Updated  1 year ago

  • granite3.2

    Granite-3.2 is a family of long-context AI models from IBM Granite fine-tuned for thinking capabilities.

    tools 2b 8b

    459.2K  Pulls 9  Tags Updated  1 year ago

  • granite-embedding

    The IBM Granite Embedding 30M and 278M models models are text-only dense biencoder embedding models, with 30M available in English only and 278M serving multilingual use cases.

    embedding 30m 278m

    372.4K  Pulls 6  Tags Updated  1 year ago

  • granite3-guardian

    The IBM Granite Guardian 3.0 2B and 8B models are designed to detect risks in prompts and/or responses.

    2b 8b

    339.5K  Pulls 10  Tags Updated  1 year ago

  • ibm/granite4.2

    IBM Granite Models are a family of enterprise-ready, open foundation models that support multilingual capabilities, coding, retrieval-augmented generation (RAG), tool use, thinking and structured JSON output. Released under Apache 2.0 license.

    3b 8b 30b

    705  Pulls 48  Tags Updated  4 weeks ago

  • dna5rm/granite4.2

    Context-optimized variant of IBM's Granite 4.2 3B model, tuned for lightweight tool-use on GPU-constrained hosts.

    65  Pulls 1  Tag Updated  3 weeks ago

  • parable/granite4.1-fable

    Parable is IBM Granite 4.1 fine-tuned on Claude Fable 5 and GPT-5.5 agent traces. Adds think reasoning to Granite. Sibling: Qwen3 line at parable/qwen3-fable

    tools thinking 3b 8b

    460  Pulls 10  Tags Updated  2 months ago

  • ibm/granite4

    Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.

    tools 350m 1b 3b

    154.4K  Pulls 261  Tags Updated  10 months ago

  • ibm/granite-docling

    Granite Docling is a multimodal Image-Text-to-Text model engineered for efficient document conversion.

    vision 258m

    19.1K  Pulls 3  Tags Updated  10 months ago

  • dna5rm/granite4.1

    Context-optimized variant of IBM's Granite 4.1 3B model, tuned for lightweight tool-use on GPU-constrained hosts.

    tools

    32  Pulls 1  Tag Updated  1 month ago

  • huihui_ai/granite3.2-abliterated

    Granite-3.2 is a family of long-context AI models from IBM Granite fine-tuned for thinking capabilities.

    tools 2b 8b

    2,755  Pulls 11  Tags Updated  1 year ago

  • huihui_ai/granite3.1-dense-abliterated

    The IBM Granite 2B and 8B models are text-only dense LLMs trained on over 12 trillion tokens of data, demonstrated significant improvements over their predecessors in performance and speed in IBM’s initial testing.

    tools 2b 8b

    1,669  Pulls 11  Tags Updated  1 year ago

  • sam860/granite-embedding-multilingual

    Embedding models supporting multiple languages, made by the IBM-Granite team, in 2 (small) sizes

    embedding

    843  Pulls 4  Tags Updated  1 year ago

  • gabegoodhart/granite-code

    Pre-release versions of IBM Granite Code models

    3b 8b 20b

    634  Pulls 6  Tags Updated  2 years ago

© 2026 Ollama
Blog Support