Inkling 2 mini: 26.4B MoE with 3.4B active matches Qwen3 27B under Apache 2.0
LiTianleli · x · 2026-11-21
An Artificial Analysis leaderboard screenshot shows Inkling 2 mini — a MoE model with 26.4B total and only 3.4B active parameters — scoring on par with Qwen3.8 27B while running significantly faster. It is released under the permissive Apache 2.0 license.
More from Models
- LeCun: Training LLMs on human knowledge yields memory, not intelligence — haider1 · 2026-11-22
- Claude veteran shocked by Gemini's leap, weighs switching to Google AI Ultra — ScreenPlayLife · 2026-11-22
- Gemini Neon builds an interactive USL lock-contention UI exposing a testing blind spot — tianyin_xu · 2026-11-22
- New spatial planning benchmark: GPT-6 and Claude Opus 5.5 fail parking route tasks — songhan_mit · 2026-11-22
- Microsoft's new models reportedly up to 80x cheaper and 50x faster — ChrisUniverse · 2026-11-22
- Inkling 2 Mini uncensored: refusals 100%→0% with a 40MB LoRA, 98% MMLU kept — Top-Eye-8104 · 2026-11-22