Xiaomi Ships Its First Local AI Host, Running a 120B Model at 1.22 TB/s

Xiaomi entered the local-AI hardware race with a workstation built to run a 120-billion-parameter model on-device, part of a broader push toward running frontier-scale models outside the cloud.

Xiaomi has released its first local AI host, according to a roundup from @TraffAlex, a workstation designed to run a 120-billion-parameter model locally with 1.22 TB/s of memory bandwidth. That bandwidth figure is the number that matters — memory throughput, not raw compute, is typically the binding constraint on how fast a large model generates tokens on local hardware.

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