Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Qwen 3.8 27B on my laptop can interpret model weights, too. Parent comment
qwen was faster in t/s, but feels like glm spends less tokens thinking and seems better at finding issues, to the point where it ends up being faster.
There are no comments on this comment yet.
qwen was faster in t/s, but feels like glm spends less tokens thinking and seems better at finding issues, to the point where it ends up being faster.