Modelpublic

MLXCreator/gemma-4-31B-it-oQ8-fp16

sourceHugging Faceupdated 4mo agoView on Hugging Face

1likes42downloads

Model Card

gemma-4-31B-it-oQ8-fp16

This model was quantized using oQ (oMLX v0.3.8) mixed-precision quantization.

Quantization details

—Model type: gemma4
—Bits: 8
—Group size: 64
—Format: MLX safetensors