DiffusionGemma
An experimental open model that explores an exceptionally fast approach to text generation
An experimental open-weights multimodal generative model family based on the Gemma 4 26B A4B Mixture-of-Experts architecture that uses discrete diffusion and block-autoregressive sampling to generate text.
Pricing
Model Intelligence
Recent stories
Google released Apache 2.0 DiffusionGemma, a 26B-A4B diffusion text model that claims up to 4x faster output by generating text in blocks instead of one token at a time. The release matters for local and hosted stacks that want to test a new decoding path.
Google's new diffusion text model picked up same-day runtime support: vLLM added native diffusion-LM serving, Unsloth shipped GGUFs, and llama.cpp got local setup guidance. That shortens the path from release to local and hosted evaluation.