cd /news/large-language-models/how-fast-is-10-tokens-per-second-rea… · home › topics › large-language-models › article
[ARTICLE · art-3605] src=simonwillison.net pub= topic=large-language-models verified=true sentiment=· neutral

How fast is 10 tokens per second really?

This article, published on May 20, 2026, highlights a simple HTML tool created by Mike Veerman that simulates different LLM token output speeds, ranging from 5 to 800 tokens per second. The tool is designed to help users visualize and understand the real-world feel of advertised speeds, such as "30 tokens per second."

read1 min views6 publishedMay 20, 2026

20th May 2026 - Link Blog How fast is 10 tokens per second really? (via) Neat little HTML app by Mike Veerman (source code here) which simulates LLM token output speeds from 5/second to 800/second. Useful if you see a model advertised as "30 tokens/second" and want to get a feel for what that actually looks like. Recent articles

  • Gemini 3.5 Flash: more expensive, but Google plan to use it for everything - 19th May 2026
  • The last six months in LLMs in five minutes - 19th May 2026
  • Notes on the xAI/Anthropic data center deal - 7th May 2026
source & further reading
simonwillison.net — original article OpenAI Help: Lockdown Mode Running Python code in a sandbox with MicroPython and WASM Quoting Andreas Kling
── more in #large-language-models 4 stories · sorted by recency
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/how-fast-is-10-token…] indexed:0 read:1min 2026-05-20 · —