𝕏xCN first seen 4 d ago, last 2 h ago, peak #1

Zhipu launches GLM-5.3-Highspeed model at 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 firm Zhipu is rolling out a new model, GLM-5.3-Highspeed, reportedly reaching generation speeds of 490 tokens per second, more than double the roughly 200 tokens per second of GLM-5.3-FlashX. The model is being gradually released through ZCode version 3.15.1, with access initially granted to randomly selected users.

Why now: The speed jump is a notable benchmark in the competitive race among Chinese AI labs to ship faster inference models.

ZhipuGLM-5.3-HighspeedGLM-5.3-FlashXZCode

Open on x →

Rank over time, top of the chart is #1. 2 snapshots from 4 h 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 · 231

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