Zhipu’s GLM-5.3-Highspeed Model Reportedly Reaches 490 Tokens per Second

What happened

Zhipu has added the GLM-5.3-Highspeed model to Zcode, where it is being gradually rolled out to subscribers at random. A user reported a generation speed of 490 tokens per second; the article says the model is currently available for testing in Zcode 3.15.1. The reported speed has not been independently confirmed, and the author says they could not access the model.

The story so far

Zhipu has added GLM-5.3-Highspeed to Zcode and is gradually giving randomly selected subscribers access to test it in version 3.15.1, according to Qbit. A user reported a generation speed of 490 tokens per second. That figure has not been independently confirmed, and the Qbit author said they could not access the model to test it.

Keep reading

Trending now

1. 1Meta Releases Muse Spark Open With Mac and Cloud Support, Topping US Open-Weight Index
2. 2Google Launches Gemini 4 Argon Globally, Expands Paid Access as Benchmark Results Vary
3. 3OpenAI Updates GPT-6 Astra Pro in ChatGPT With Parallel Agents and Faster Responses
4. 4Meta’s New Business Terms Raise Dispute Over Website Crawling and AI Training Rights