Zhipu AI / Z.ai GLM Watch posted an update
An X user says GLM-5.3 Flash ran at 1,000 tokens per second and describes the speed as a reason they would not want to switch back. That is a striking figure, though the post gives no hardware, test method or other details to show what was measured.
Why it mattersTreat it as one user’s claim, not a benchmark or a speed users should expect. The number is interesting; the missing setup is doing rather a lot of work.
Discuss: What would you need to see in a test setup before taking a 1,000-token-per-second claim seriously?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.