How to use nkamiy/Qwen3-VL-Embedding-8B-8bit-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3-VL-Embedding-8B-8bit-mlx nkamiy/Qwen3-VL-Embedding-8B-8bit-mlx
