How to use mlx-community/CodeQwen1.5-7B-Chat-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir CodeQwen1.5-7B-Chat-4bit mlx-community/CodeQwen1.5-7B-Chat-4bit
wangdawang