DeepSeek-V4.1-Flash hits 675.9 tok/s decode on 4× RTX PRO 6000 workstation
0xSero · x · 2026-10-22
0xSero shared a local inference benchmark: DeepSeek-V4.1-Flash-1017 running original weights on 4× RTX PRO 6000 (4×96GB) reaches 675.9 tok/s decode at concurrency 1, with a 528K context window, as measured by Sybil AI's dashboard. Inference recipes are promised to follow, showing workstation-class hardware can now serve large open models at very high single-user speed.
More from Infra
- Cadence announces sovereign AI cloud for European chip designers — karlfreund · 2026-10-23
- SGLang Deep-Dive Blog Series Breaks Down KV Cache, Posts up to 15.5x Throughput Gains — BanghuaZ · 2026-10-23
- DynaLM: Open-Source CPU-First LLM Inference Engine Seeks Feedback — Unlikely_Safety_7456 · 2026-10-23
- Capital Is Now the AI Buildout Bottleneck, Says Analyst Citing Jensen Huang — JOBhakdi · 2026-10-23
- Cerebras explains how it deploys trillion-parameter models on wafer-scale chips — bookwormengr · 2026-10-23
- IFM open-sources RL360, the agentic RL infra behind K2 Horizon's training — rupspace · 2026-10-23