DeepSeek V4 Flash Runs Agentic Workloads Locally at 31 Tokens/Sec on an M3 Ultra

The open-model camp keeps closing the gap: DeepSeek's V4 Flash is drawing attention for single-box agentic performance that runs entirely on consumer-grade hardware.

While the frontier labs chase million-token budgets, the open-model camp is winning a different race — local, private, cheap. @marcopapa99 reports that DeepSeek V4 Flash "looks nasty on single-box agent workloads," running locally on an M3 Ultra at 31 tokens per second. That last figure is the one that matters.

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