Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I got 700+ tokens/sec on o3 after the announcement, I suspect it's very much a quantized version.

https://x.com/hyperknot/status/1932476190608036243



Or maybe they just brought online much faster much cheaper hardware.


Or they are using a speedy add-on decoder.


Do you also have numbers on intelligence before and after?


Is that input tokens or output tokens/s?




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: