How to use zviratko/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-oQ4e-fp16-mtp with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-oQ4e-fp16-mtp zviratko/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-oQ4e-fp16-mtp
library_name: mlx tags: - mlx - oq - quantized base_model: - DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP
This model was quantized using oQ (oMLX v0.6.3) mixed-precision quantization.
