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:
- For the same Intelligence Index score as Qwen3.8 27B, it emits 38% more output tokens (152K vs 110K per task) but uses 2.8x less compute on the active-parameters × tokens proxy, and 5x less than Nanbeige4.3-33B.
- The trick: 12 of its 24 layers run three times per token, adding compute without adding output tokens — trading hidden-layer loops for a faster, cheaper user experience.
Related event: Inkling 2 Mini Matches Qwen3.8 27B With a Fifth of the Active Parameters(2 posts)→
More from Models
- Gemini 4 Neon locked to Pro and Ultra paid subscribers, leaving Plus users out — giffmana · 2026-11-21
- Looped transformers: more looping boosts reasoning but with diminishing returns past 3 passes and fewer CoT tokens — nrehiew_ · 2026-11-21
- Team releases TML-d24-varloop-research on Hugging Face to study looping's effect on CoT monitorability — nrehiew_ · 2026-11-21
- Full sub-benchmark breakdown for Inkling 2 Mini published by Artificial Analysis — ArtificialAnlys · 2026-11-21
- Inkling 2 Mini costs ~6x less and runs ~4x faster per task than Qwen3.8 27B, AA finds — ArtificialAnlys · 2026-11-21
- Inkling 2 Mini matches 27B-33B rivals on intelligence with ~5-6x fewer active parameters — ArtificialAnlys · 2026-11-21