The Keyword ·

Google introduces DiffusionGemma, an experimental 26B-parameter open model that uses text diffusion for faster text generation compared to autoregressive models

Our newest open experimental model delivers up to 4x faster inference on dedicated GPUs and opens the door to exploring speed-critical, interactive local workflows.

Google introduces DiffusionGemma, an experimental 26B-parameter open model that uses text diffusion for faster text generation compared to autoregressive models

Lead Source

How this story grew

Coverage · 0 Discussion · 0
Jun 10Jun 11

More

Hugging Face: Hugging Face
Decrypt: Decrypt
Ars Technica: Ars Technica
Tech Monitor: Tech Monitor
Android Authority: Android Authority
The Fast Mode: The Fast Mode
SiliconANGLE: SiliconANGLE
Unsloth: Unsloth
Google Developers Blog: Google Developers Blog
The Decoder: The Decoder
MarkTechPost: MarkTechPost
Let's Data Science: Let's Data Science
Exploring Language Models: Exploring Language Models
The New Stack: The New Stack

Discussion

TechSnif Coverage

Google Drops DiffusionGemma: Text Diffusion Takes On Autoregressive AI

Google's new 26B-parameter open model uses text diffusion to achieve up to 4x faster inference than traditional approaches.

Google just released DiffusionGemma, an experimental open model that ditches the standard autoregressive approach to text generation in favor of text diffusion. The result? Up to 4x faster inference when running on dedicated GPUs.

The model packs 26 billion parameters and is designed to unlock speed-critical, interactive local workflows. That's a meaningful shift — most large language models generate text one token at a time. Diffusion-based generation works differently, potentially producing text in parallel chunks.

DiffusionGemma is open and experimental, meaning researchers and developers can dig into it immediately. Google is positioning it as an exploration tool rather than a production-ready system.

The big picture: if diffusion-based text generation proves viable at scale, it could fundamentally change how fast AI models respond — especially for local, on-device applications where latency matters most.