How to use apocryphx/gemma-4-31b-it-qat-q4-g32-apml with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir gemma-4-31b-it-qat-q4-g32-apml apocryphx/gemma-4-31b-it-qat-q4-g32-apml
