MLX

Llama 3.2 1B Instruct 4bit

Meta

llama

A tiny and speedy Llama model from Meta, optimized for multilingual dialogue use cases

Model info

Model

Llama 3.2 1B Instruct 4bit

Author

Meta

Arch

llama

Parameters

1b

Format

safetensors

Size on disk

about 704.45 MB

Download and run Llama 3.2 1B Instruct 4bit

Open in LM Studio to view download options

Download llama-3.2-1b from the terminal

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

lms get llama-3.2-1b

Call llama-3.2-1b from your code

curl http://localhost:1234/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.2-1b",
    "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


lmmy