Power sharing fits 192 GB300 GPUs in 140-GPU power budget, boosting tokens/s by 49%
julsimon · x · 2026-09-28
Citing NVIDIA and Nscale's own test (Sep 27), 140 GB300 GPUs drew only 166.2 kW of a 264.4 kW budget. With power sharing, 192 GPUs fit the same budget, delivering 49.2% more tokens per second — at the cost of a 17% longer wait for the slowest 1% of requests. Part of AI's power shortage, the author notes, is power reserved and never used.
More from Infra
- AI's Power Paradox: Data Centers Strain Grid While AI Agents Optimize Energy — ingliguori · 2026-09-28
- Beyond 2-4 GPUs there are no off-the-shelf cases, says HF dev planning 3D-printed shrouds — TheZachMueller · 2026-09-28
- The biggest buildout in history: data centers are industrializing intelligence — Dr_Singularity · 2026-09-28
- Anthropic's Contracted Value Exceeds $180B, Per NVIDIA — zephyr_z9 · 2026-09-28
- David Friedberg: Open-Source Models Make Data Centers Unnecessary for 90% of AI Use — MarvinTBaumann · 2026-09-28
- Old-School Infra Engineers on PB-Scale AI Logs: Hadoop Did This on a Tuesday — basedjensen · 2026-09-28