Skip to content
Google DeepMind·· 2026-06-11SelectedAI score70

DiffusionGemma: 4x faster text generation

DiffusionGemma: 4x faster text generation

AI introduction

Google DeepMind released DiffusionGemma, an open-source experimental model that generates whole blocks of text via a text diffusion approach, achieving up to 4x inference speedups on dedicated GPUs (over 1,000 tokens/second on an NVIDIA H100 and over 700 tokens/second on an RTX 5090).

Why it matters

The official release specifies the hardware behind the 4x speedup and output quality trade-offs, letting readers judge whether it suits local low-concurrency workloads.

A summary is available. Open the original source for the full article. Read source
Source images · Select to enlarge

Source: Google DeepMind · deepmind.google

#模型发布#开源生态#推理#Google#DeepMind