How to use sensiarion/embeddinggemma-300m-code-8L-distill-int8 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir embeddinggemma-300m-code-8L-distill-int8 sensiarion/embeddinggemma-300m-code-8L-distill-int8
