How to use michaellin/gemma-4-12B-it-qat-4bit-gs32 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir gemma-4-12B-it-qat-4bit-gs32 michaellin/gemma-4-12B-it-qat-4bit-gs32
