DiffusionGemma: The Developer Guide- Google Developers Blog
Jun 10, 2026Ian Ballantyne, Omar Sanseviero

Summary
This post introduces DiffusionGemma, an experimental model built on the Gemma 4 backbone, which offers compute-bound parallel generation, bidirectional context and self-correction, and developer-friendly sizes. It details the architecture, including uniform state diffusion and block autoregressive diffusion for variable length generation. The post showcases its ability to solve Sudoku puzzles through parallel denoising and error correction via re-noising. It also provides guidance on serving DiffusionGemma using vLLM and links to resources for downloading weights, learning more, and adapting/fine-tuning the model.
More from the Diffusion Models for Text Generation trail
- Introducing Veo 3.1 and new creative capabilities in the Gemini API- Google Developers Blog
- Own your AI: Learn how to fine-tune Gemma 3 270M and run it on-device- Google Developers Blog
- Gemini 2.5 Flash Image now ready for production with new aspect ratios- Google Developers Blog
- Unlocking Multi-Spectral Data with Gemini- Google Developers Blog
- Introducing EmbeddingGemma: The Best-in-Class Open Model for On-Device Embeddings- Google Developers Blog