A 744-Billion-Parameter Model Now Runs at Home on 300 Watts

GLM-5.2 running across three DGX Sparks pulls roughly the power of three lightbulbs — a data point on how fast frontier-scale inference is escaping the cloud.

A striking benchmark surfaced from the local-inference community: @MiaAI_lab reported running a 744-billion-parameter model — GLM-5.2 — at home on roughly 300 watts total, spread across three DGX Sparks. For context, 300 watts is a gaming PC under load, or three incandescent bulbs. A three-quarters-of-a-trillion-parameter model at that power envelope would have been implausible a year ago.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia curae.

Pellentesque habitant morbi tristique senectus et netus et malesuada fames ac turpis egestas. Proin pharetra nonummy pede. Mauris et orci. Aenean nec lorem. In porttitor. Donec laoreet nonummy augue. Suspendisse dui purus, scelerisque at, vulputate vitae, pretium mattis, nunc. Mauris eget neque at sem venenatis eleifend. Ut nonummy. Fusce aliquet pede non pede. Suspendisse dapibus lorem pellentesque magna integer malesuada.

Unlock the full briefing

Get every story in today's briefing, the full archive, and the daily AI intelligence brief.

All stories today

Full archive

Daily brief