How to use pxleng/GLM-5.3-Flash-UNCENSORED-oQ4e-mtp with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download pxleng/GLM-5.3-Flash-UNCENSORED-oQ4e-mtp --local-dir GLM-5.3-Flash-UNCENSORED-oQ4e-mtp
https://huggingface.co/pxleng/GLM-5.3-Flash-UNCENSORED-oQ4e-mtp/resolve/main/README.md
hf download hf://pxleng/GLM-5.3-Flash-UNCENSORED-oQ4e-mtp/README.md
curl -L -o README.md https://huggingface.co/pxleng/GLM-5.3-Flash-UNCENSORED-oQ4e-mtp/resolve/main/README.md
library_name: mlx tags: - mlx - oq - quantized
This model was quantized using oQ (oMLX v0.7.0.dev2) mixed-precision quantization.
