mlx-community/diffusiongemma-26B-A4B-it-OptiQ-4bit

Quantization vs google/diffusiongemma-26B-A4B-it. mlx-community/diffusiongemma-26B-A4B-it-OptiQ-4bit is a quantized version of the other (U32/BF16).

On the Hub · Downloads on Model Pulse