antirez Optimizes DwarfStar: 170 t/s Generation and 22k tokens/s Prefill on Station

antirez · x · 2026-08-17

antirez was asked about DwarfStar's performance on Station with MXFP4 and the Flash model instead of PRO. After about 48 hours of optimization, it achieves 170 t/s generation without DFlash and 22k tokens/s prefill, with potential for further improvement.

Related event: antirez Tunes DwarfStar to 170 t/s Generation on Station(2 posts)→

Original post →

More from Infra

Infra channel →