How to use mlx-community/Qwen2-Audio-7B-Instruct-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen2-Audio-7B-Instruct-4bit mlx-community/Qwen2-Audio-7B-Instruct-4bit
