Jp¥online 繁中简中EN2026/06/11
TECH & INNOVATION

Google's DiffusionGemma Generates 1,000+ Tokens a Second on a Local GPU

Source: ITmedia AI+· Published: 2026/06/11 12:00 JST· Section: TECH & INNOVATION
# Google# DiffusionGemma# diffusion models# local AI
Key Points
  • The experimental model applies image-style diffusion to text generation
  • It produces 256 tokens in parallel, up to 4x faster than autoregressive models
  • Quality trails standard models; strengths are local inline editing and code completion
Analysis

Google's experimental DiffusionGemma ports image-diffusion techniques to text, generating 256 tokens in parallel for up to 4x speed — past 1,000 tokens a second on a local GPU. It trades some quality for speed, aiming at local inline editing and code completion.

Read the original (ITmedia AI+) → ← Back to home