𝕏xCN first seen 1 d ago, last 2 h ago, peak #1

Zhipu's new GLM model reportedly hits 490 tokens per second

Original: BREAKING: Zhipu appears to have a new GLM model hitting 490 tokens/s. GLM-5.3-Highspeed runs more than 2× faster than GL

Chinese AI company Zhipu is reported to be releasing GLM-5.3-Highspeed, a new model in its GLM family said to generate up to 490 tokens per second, more than double the roughly 200 tokens per second of GLM-5.3-FlashX. The model is said to be rolling out gradually in ZCode 3.15.1, with access initially available to some users at random.

Why now: A new, significantly faster model from a leading Chinese AI lab has just started rolling out, drawing attention from developers tracking the GLM lineup.

ZhipuGLM-5.3-HighspeedGLM-5.3-FlashXZCode

Open on x →

Rank over time, top of the chart is #1. 4 snapshots from 1 d ago to 2 h ago.

Evidence

• BREAKING: Zhipu appears to have a new GLM model hitting 490 tokens/s. GLM-5.3-Highspeed runs more than 2× faster than GLM-5.3-FlashX, which peaks at around 200 tokens/s. The model is currently rolling out gradually in ZCode 3.15.1, with access randomly available to · Chinazhidx · 232

API: https://socialmediatrends-api.osmike.com/v1/trends/1945665