Inkling 2 Mini Matches Qwen3.8 27B With a Fifth of the Active Parameters
Artificial Analysis finds Inkling 2 Mini matches Qwen3.8 27B's Intelligence Index using about a fifth of the active parameters, emitting 38% more tokens while requiring 2.8x less compute thanks to its recurrent-layer design.
2026-11-21 ~ 2026-11-21 · 2 related posts
- Inkling 2 Mini matches 27B-33B rivals on intelligence with ~5-6x fewer active parameters — ArtificialAnlys · 2026-11-21
- Looped layers let Inkling 2 Mini use ~2.8x less compute despite 38% more output tokens — ArtificialAnlys · 2026-11-21