RTX 3090 power can be dialed down to 120W for inference, saving power and heat
QuixiAI · x · 2026-10-01
loktar00 notes that most people just set their RTX 3090s at 210-240W and forget about it. He tested power limits all the way down to 120W and found they still work fine for inference — cutting power draw and heat significantly. Useful tip for multi-GPU local deployments.
More from Infra
- Magnitude (YC S25) Open-Sources Inference Engine with Up to 2x Faster Decode Than llama.cpp — petrusenko_max · 2026-10-01
- Chinese labs reportedly buying expert training data from US data firms like Mercor and SurgeAI — BarnacleBasic1988 · 2026-10-01
- Andrew Chen: The $20K workstation era is back — RTX PRO 6000 and Mac Studio — andrewchen · 2026-10-01
- PyTorch Foundation's Mark Collier: open source is the coordination layer for frontier AI — PyTorch · 2026-10-01
- Qwen 27B Now Runs on AMD NPUs via FastFlowLM, at a Slow 1 tps — TuskNaPrezydenta2020 · 2026-10-01
- Cognition Becomes First CoreWeave Vera Rubin NVL72 Customer, Sees 4.8X SWE-2 Throughput Boost — altryne · 2026-10-01