Back to feed
News & Blog - DeepMind
News & Blog - DeepMind
6/10/2026
DiffusionGemma: 4x faster text generation

DiffusionGemma: 4x faster text generation

Short summary

Google DeepMind announced DiffusionGemma, achieving 4x faster text generation compared to prior versions. The update to the Gemma model family improves inference speed significantly. Details on implementation, benchmarks, and availability would guide adoption.

  • DiffusionGemma delivers 4x faster text generation
  • Improvement to Google's Gemma model family
  • Announced by Google DeepMind on 2026-06-10

Generated with AI, which can make mistakes.

Is this a good recommendation for you?

Explore more