How to use mlx-community/DeepSeek-R1-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir DeepSeek-R1-4bit mlx-community/DeepSeek-R1-4bit
it can use vllm? or only mlx
· Sign up or log in to comment