How to use majentik/Qwen3-Embedding-4B-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3-Embedding-4B-MLX-4bit majentik/Qwen3-Embedding-4B-MLX-4bit
majentik commited on 