Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on GPT-OSS Reinforcement Learning. Parent comment
Which means it has ~3b parameters active per token.
Qwen3-32b has 32b params active per token
There are no comments on this comment yet.
Which means it has ~3b parameters active per token.
Qwen3-32b has 32b params active per token