How to use scottlowry/Qwen3.5-122B-A10B-oQ4e-fp16-mtp with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download scottlowry/Qwen3.5-122B-A10B-oQ4e-fp16-mtp --local-dir Qwen3.5-122B-A10B-oQ4e-fp16-mtp
https://huggingface.co/scottlowry/Qwen3.5-122B-A10B-oQ4e-fp16-mtp/resolve/main/README.md
hf download hf://scottlowry/Qwen3.5-122B-A10B-oQ4e-fp16-mtp/README.md
curl -L -o README.md https://huggingface.co/scottlowry/Qwen3.5-122B-A10B-oQ4e-fp16-mtp/resolve/main/README.md
library_name: mlx tags: - mlx - oq - quantized base_model: - Qwen/Qwen3.5-122B-A10B
This model was quantized using oQ (oMLX v0.5.3) mixed-precision quantization.
