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)→
More from Infra
- First AA-AgentPerf results: NVIDIA Vera Rubin NVL72 delivers up to 5.7x throughput per MW vs GB300 — ArtificialAnlys · 2026-10-16
- Vera Rubin NVL72 first benchmarks: up to 5.7x throughput per MW vs GB300 — ArtificialAnlys · 2026-10-16
- NVIDIA Vera Rubin NVL72 hits up to 5.7x GB300 throughput per MW on agent benchmark — ArtificialAnlys · 2026-10-16
- 14 open-source LLM observability tools to know in 2026, from Langfuse to Laminar — TheTuringPost · 2026-10-16
- Local AI is a routing problem, not a privacy feature: where each task should run — bigdata · 2026-10-16
- Moving agent work from GPUs to CPUs for durable, predictable actions — cramforce · 2026-10-16