ekryski
/

diffusiongemma-26B-A4B-it-4bit

diffusion_gemma

4-bit precision

Model card Files Files and versions

diffusiongemma-26B-A4B-it-4bit / model-00001-of-00004.safetensors

Commit History

v2: fused experts (4-bit) + 4-bit embeddings, even ~3.84GB shards (FFAI ffai convert)

2339bc7
verified

ekryski commited on Jun 10