MLX

DeepSeek Coder V2 Lite Instruct 4bit mlx

mlx-community

deepseek

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

Model info

Model

DeepSeek Coder V2 Lite Instruct 4bit mlx

Author

mlx-community

Arch

deepseek

Parameters

16B

Format

safetensors

Size on disk

about 8.84 GB

Download and run DeepSeek Coder V2 Lite Instruct 4bit mlx

Open in LM Studio to view download options

Download deepseek-coder-v2 from the terminal

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

lms get deepseek-coder-v2

Call deepseek-coder-v2 from your code

curl http://localhost:1234/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-coder-v2",
    "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