DiffusionGemma

⋅

DiffusionGemma

Last May Google briefly released an experimental Gemini Diffusion model. I tried the preview at the time and recorded it running at 857 tokens/second. It was an exciting model, but Google made no further announcements about it.

That research has returned in the best possible way: as a new open weight (Apache 2 licensed) Gemma model, google/diffusiongemma-26B-A4B-it.

NVIDIA are currently hosting the model for free on their NIM cloud API. I used that API to generate this pelican, which took 4.4s (according to time uv run generate.py) to return 2,409 tokens – so at least 500 tokens/second.

Flat minimalist illustration of a white pelican with a large orange beak riding a red bicycle with black wheels, against a pale blue background with a green line representing the ground

Via Hacker News

Tags: google, ai, generative-ai, llms, nvidia, pelican-riding-a-bicycle, gemma, llm-release, llm-performance

Liked Liked