Looped layers let Inkling 2 Mini use ~2.8x less compute despite 38% more output tokens

ArtificialAnlys · x · 2026-11-21

Artificial Analysis broke down Inkling 2 Mini's compute economics:

Related event: Inkling 2 Mini Matches Qwen3.8 27B With a Fifth of the Active Parameters(2 posts)→

Original post →

More from Models

Models channel →