How to use mlx-community/Meta-Llama-3-120B-Instruct-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Meta-Llama-3-120B-Instruct-4bit mlx-community/Meta-Llama-3-120B-Instruct-4bit
