[!IMPORTANT] This quantization was uploaded on 2026-06-18 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.

diffusiongemma-26B-A4B-it-oQ2.7-fp16

Quantization details

• Model type: diffusion_gemma
• Bits: 2
• Group size: 64
• Format: MLX safetensors