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

GPUs can't reach these speeds. You could build a supercomputing cluster and still not reach these speeds.
 help



MiMo-V2.5-Pro-UltraSpeed gets pretty close with over 1000 TPS on 8x B200. It has 1.02T total parameters and 42B active, compared to 27B total/active for Qwen3.8-27B. Also, B300 are out now. I think 1500 TPS for Qwen3.8-27B should be doable.

That model uses a lot of tricks to achieve 1000 t/s. I would not use raw parameter counts alone for such comparisons, in general.

Celeris reaches ~50% of the speed on commodity hardware. celeris-magnus-1 is based on qwen3.8-27b. Maybe we will get there without custom silicon!



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

Search: