# Bookmarked: Gemini Diffusion

- Author: @gurupanguji
- Date: 2025-05-29
- URL: https://gurupanguji.com/blog/2025/05/29/gemini-diffusion/
- Categories: link, technology
- Tags: diffusion, gemini, io, llm, models

---


> The key feature then is speed. I made it through the waitlist and tried it out just now and wow, they are not kidding about it being fast. In this video I prompt it with "Build a simulated chat app" and it responds at 857 tokens/second, resulting in an interactive HTML+JavaScript page (embedded in the chat tool, Claude Artifacts style) within single digit seconds.

*Source:* [Gemini Diffusion](https://simonwillison.net/2025/May/21/gemini-diffusion/#atom-everything)

<!-- wp:paragraph -->
<p>This is the worst it will be. That makes it incredibly impressive and is nothing short of a novel way to improve token outputs. I can only imagine how this could be implemented in parts of the LLM paths to make the process so much faster. </p>
<!-- /wp:paragraph -->

<!-- wp:paragraph -->
<p>Fascinating. </p>
<!-- /wp:paragraph -->