Zhipu's GLM-5.3-Highspeed reportedly runs at 490 tokens/s in Zcode
Overview
QbitAI reports that Zhipu's GLM-5.3-Highspeed model is available to some Zcode 3.15.1 subscribers, and one user reported a speed of 490 tokens/s.
QbitAI could not test the model because it was not yet available on its account, so the speed figure is the user's report, not QbitAI's measurement.
For comparison, QbitAI cites GLM-5.3-FlashX, released last month, with a top speed of 200 tokens/s. It also cites Artificial Analysis, which measured GLM-5.3-Flash at about 60 tokens/s on the Z.ai API.
Written by AI from the articles below · updated Oct 12, 12:54 AM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- QbitAINewsZhipu's GLM-5.3-Highspeed reportedly reaches 490 tokens/s in Zcode
AIZhipu's GLM-5.3-Highspeed model is reportedly available to random Zcode 3.15.1 subscribers, with one user reporting a speed of 490 tokens/s. That is well above the 200 tokens/s top speed of GLM-5.3-FlashX released last month, and Artificial Analysis measured GLM-5.3-Flash at about 60 tokens/s on the Z.ai API. QbitAI could not test the model because it was not yet available to its account.
Heat trend
Not enough continuous observations to show a trend yet.