Granite 4.0 models

Granite 4.0 models are finetuned from their base models using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets. They feature improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.

Please Note: the 3b, 1b, and 350m model sizes are alternative options for users when mamba-2 support is not yet optimized. Models denoted -h use the hybrid mamba-2 architecture.

Parameter Sizes

350m

ollama run granite4:350m

350m-h

ollama run granite4:350m-h

1b

ollama run granite4:1b

1b-h

ollama run granite4:1b-h

3b (micro)

ollama run granite4:3b
ollama run granite4:micro

3b-h (micro-h)

ollama run granite4:3b-h
ollama run granite4:micro-h

7b-a1b-h (tiny-h)

ollama run granite4:7b-a1b-h
ollama run granite4:tiny-h

32b-a9b-h (small-h)

ollama run granite4:32b-a9b-h
ollama run granite4:small-h

Supported Languages

English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. Users may finetune Granite 4.0 models for languages beyond these languages.

Intended Use

This model is designed to handle general instruction-following tasks and can be integrated into AI assistants across various domains, including business applications.

Capabilities

• Summarization
• Text classification
• Text extraction
• Question-answering
• Retrieval Augmented Generation (RAG)
• Code related tasks
• Function-calling tasks
• Multilingual dialog use cases
• Fill-In-the-Middle (FIM) code completions

Learn more

• Developers: Granite Team, IBM
• Website: Granite Docs
• GitHub Repository: ibm-granite/granite-4.0-language-models
• Release Date: October 2nd, 2025
• License: Apache 2.0