How to use scottlowry/Qwen2.5-Coder-7B-oQ8e with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen2.5-Coder-7B-oQ8e scottlowry/Qwen2.5-Coder-7B-oQ8e
