Granite-3.2 is a family of long-context AI models fine-tuned for thinking capabilities. Built on top of Granite-3.1, it has been trained using a mix of permissively licensed open-source datasets and internally generated synthetic data designed for reasoning tasks. The models allow controllability of its thinking capability, ensuring it is applied only when required.

• Developers: Granite Team, IBM
• Website: Granite Docs
• Release Date: February 26th, 2025
• License: Apache 2.0

Sizes

The models are available in two parameter sizes, 2B and 8B:

ollama run granite3.2:2b

ollama run granite3.2:8b

Supported Languages: English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. However, users may finetune this Granite model for languages beyond these 12 languages.

Intended Use: These models are designed to handle general instruction-following tasks and can be integrated into AI assistants across various domains, including business applications.

Capabilities

• Thinking
• Summarization
• Text classification
• Text extraction
• Question-answering
• Retrieval Augmented Generation (RAG)
• Code related tasks
• Function-calling tasks
• Multilingual dialog use cases
• Long-context tasks including long document/meeting summarization, long document QA, etc.

Thinking

To enable thinking, add a message with "role": "control" and set "content" to "thinking". For example:

{
    "messages": [
        {"role": "control", "content": "thinking"},
        {"role": "user", "content": "How do I get to the airport if my car won't start?"}
    ]
}

References

Website