How to use zviratko/gemma-4-12B-it-oQ4e-fp16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir gemma-4-12B-it-oQ4e-fp16 zviratko/gemma-4-12B-it-oQ4e-fp16
library_name: mlx tags: - mlx - oq - quantized base_model: - google/gemma-4-12B-it
This model was quantized using oQ (oMLX v0.5.1) mixed-precision quantization.
