How to use zaydiscold/Qwen2.5-7B-Instruct-MLX-2bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen2.5-7B-Instruct-MLX-2bit zaydiscold/Qwen2.5-7B-Instruct-MLX-2bit
