Yes, we are back👑, with 206 tok/s on a single RTX 5090! Amazing Day-0 work from
Source
x.com
Author
Alibaba_Qwen
Date
Why it matters
A current-generation 27B dense model decoding at over 200 tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → per second on one consumer GPU puts local AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → loops within reach without server hardware.
Terms in this piece · Glossary
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
