Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.
765.5K Pulls 17 Tags Updated 4 months ago
IBM Granite 2B and 8B models are 128K context length language models that have been fine-tuned for improved reasoning and instruction-following capabilities.
916.3K Pulls 3 Tags Updated 10 months ago
The IBM Granite 1B and 3B models are long-context mixture of experts (MoE) Granite models from IBM designed for low latency usage.
2.3M Pulls 33 Tags Updated 1 year ago
A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
785.7K Pulls 5 Tags Updated 1 year ago
A family of open foundation models by IBM for Code Intelligence
728.4K Pulls 162 Tags Updated 1 year ago
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.
436.8K Pulls 33 Tags Updated 1 year ago
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.
438.3K Pulls 33 Tags Updated 1 year ago
Granite-3.2 is a family of long-context AI models from IBM Granite fine-tuned for thinking capabilities.
283.8K Pulls 9 Tags Updated 1 year ago
The IBM Granite 1B and 3B models are the first mixture of experts (MoE) Granite models from IBM designed for low latency usage.
397.7K Pulls 33 Tags Updated 1 year ago
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.
220.8K Pulls 6 Tags Updated 1 year ago
The IBM Granite Guardian 3.0 2B and 8B models are designed to detect risks in prompts and/or responses.
158.3K Pulls 10 Tags Updated 1 year ago
A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.
2.1M Pulls 119 Tags Updated 2 years ago
14.6K Pulls 261 Tags Updated 4 months ago
Granite Docling is a multimodal Image-Text-to-Text model engineered for efficient document conversion.
4,883 Pulls 3 Tags Updated 3 months ago
This is essentially a Completely UNCENSORED version of Granite4. NJOY!!!
550 Pulls 1 Tag Updated 1 month ago
Efficient, intelligent, and tiny models from IBM
684 Pulls 17 Tags Updated 4 months ago
Granite Docling is a multimodal Image-Text-to-Text model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
517 Pulls 2 Tags Updated 4 months ago
Granite-4.0-H-350M is a lightweight instruct model finetuned from Granite-4.0-H-350M-Base using a combination of open-source instruction datasets with permissive license and internally collected synthetic datasets.
300 Pulls 16 Tags Updated 3 months ago
168 Pulls 2 Tags Updated 4 months ago
51.9K Pulls 64 Tags Updated 6 months ago