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-oQ4-fp16
This model was quantized using oQ (oMLX v0.4.4) mixed-precision quantization.
Quantization details
- Model type: diffusion_gemma
- Bits: 4
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- -
Model size
4B params
Tensor type
F16
·
U32 ·
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support