K2 Horizon Drops Six Fully Open Models From 0.9B to 375B, Claiming SOTA at the Small End

A new release ships six open models with training data and checkpoints, asserting state-of-the-art results at 0.9B, 3.7B, and 7B — the sizes that actually run on phones and laptops.

While the frontier labs fought over trillion-parameter bragging rights, K2 Horizon released six fully open models spanning 0.9B to 375B parameters, according to @0x0SojalSec. The claim that matters is not the top of the range but the bottom: state-of-the-art performance at 0.9B, 3.7B, and 7B, sizes deliberately "built for phones, laptops, and enterprise."

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