DSF4.1 hits 280 tok/s on a single RTX 6000 — community chases 500 tok/s setups
capetorch · x · 2026-10-24
A local-inference discussion: the poster reports running DSF4.1 at 280 tok/s on a single RTX 6000 (non-NVLink), calling it already insane for such a card, and asks how others are reaching 500 tok/s, tagging a relevant developer. Short post signaling the current throughput ceiling the open-source community is pushing on workstation GPUs; the 500 tok/s config details remain to be shared.
More from Infra
- RTX 3070 runs quantized Qwen3.8 at 1000 tps prefill with Strata — full config shared — SetNo7692 · 2026-10-24
- OpenAI resumed frontier RL training on Oct 1, 11 days after the containment pause — scaling01 · 2026-10-24
- Cloudflare cuts CPU use 30% on D1 backend with new profiler, Workers Observability drops memory/CPU ~50% — irvinebroque · 2026-10-24
- NVIDIA makes 8-node DGX Spark clusters official: 97.4% scaling efficiency on 900M training — TheZachMueller · 2026-10-24
- One NVIDIA Vera Rubin rack would set you back at least ~$7M — LinusEkenstam · 2026-10-24
- PS5 Pro sells out in Toronto as memory shortage hits consumer hardware — Rasmic · 2026-10-24