Granite 3.1 8B

IBM

granite

Dense LLM from IBM supporting up to 128K context length, trained on 500B tokens. Suitable for general instructions following and can be used to build AI assistants

Model info

Model

Granite 3.1 8B

Author

IBM

Arch

granite

Parameters

8B

Format

gguf

Size on disk

about 4.94 GB

Download and run Granite 3.1 8B

Open in LM Studio to view download options

Download granite-3.1-8b from the terminal

Download the model using lms — LM Studio's developer CLI.

lms get granite-3.1-8b
If you don't have it yet, get it by running npx lmstudio install-cli

Call granite-3.1-8b from your code

curl http://localhost:1234/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "granite-3.1-8b",
    "messages": [
      { "role": "system", "content": "Always answer in rhymes." },
      { "role": "user", "content": "Introduce yourself." }
    ],
    "temperature": 0.7,
    "max_tokens": -1,
    "stream": true
  }'

Next Steps: Build! 🔨

Learn more