DeepSeek-V4.1-Flash Throughput Benchmarked Across 3 Tools on 4x RTX PRO 6000
TheZachMueller · x · 2026-11-03
A hands-on throughput benchmark of DeepSeek-V4.1-Flash-1017 on 4x RTX PRO 6000 GPUs with Engram RAM offload, testing 3 checkpoint variants across llm-inference-bench, NVIDIA Dynamo AIPerf, and SemiAnalysis AgentX, with and without DSpark up to 7 speculative draft tokens — arguing you should know where your inference server saturates.
More from Infra
- Google's Suncatcher satellite runs Gemma 270mi n space—power limits mean only one TPU lit at a time — demian_ai · 2026-11-03
- Mistral VP: Le Chonk trained on just 10 MW (~4,000 H100s), begs investors for 1 gigawatt — _AndrewZhao · 2026-11-03
- UCSB awards IEE seed funding to three ECE projects on energy-efficient AI and quantum hardware — ninamiolane · 2026-11-03
- Europe's Physical AI Agenda: Gigafactories, Sovereign Compute and AI Act Rules — ingliguori · 2026-11-03
- Weight teleportation open-sourced: cross-datacenter RL weight updates under 0.23s — gharik · 2026-11-03
- YouTuber's "F-You to Sam Altman" video showcases a local AI GPU rig — unchikuso · 2026-11-03