Duplicated from mlx-community/gemma-4-e4b-it-4bit
How to use ashudesai/gemma-4-e4b-it-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download ashudesai/gemma-4-e4b-it-4bit --local-dir gemma-4-e4b-it-4bit
