How to use Jundot/gemma-4-26B-A4B-it-oQ6 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir gemma-4-26B-A4B-it-oQ6 Jundot/gemma-4-26B-A4B-it-oQ6
library_name: mlx tags: - mlx - oq - quantized
This model was quantized using oQ (oMLX v0.3.5) mixed-precision quantization.
