Duplicated from EschaLabs/escha-runtime-qwen3moe
How to use r3lax/escha-runtime-qwen3moe with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir escha-runtime-qwen3moe r3lax/escha-runtime-qwen3moe
