How to use shadowrock-io/Nemotron-3-Embed-8B-Community-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Nemotron-3-Embed-8B-Community-MLX-4bit shadowrock-io/Nemotron-3-Embed-8B-Community-MLX-4bit
