DFlash 2 Hits 70 Tokens/Second on a MacBook, 4.6x Standard Decoding

A new speculative-decoding technique reportedly reaches 70 tokens per second on consumer Apple hardware, roughly 4.6 times the speed of standard autoregressive generation.

Local inference keeps getting faster. @TraffAlex reported that DFlash 2 hits 70 tokens per second on a MacBook — about 4.6 times the speed of standard autoregressive decoding. For anyone who has watched a local model dribble out text token by token, a near-fivefold speedup is the difference between a novelty and a usable tool.

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