Thinking Machines launches Inkling 2 Mini: 26B looped transformer that runs on a laptop, scores 20.1 on AA Index
LiTianleli · x · 2026-11-21
Thinking Machines officially announced Inkling 2 Mini — after some users found the 594B-parameter Inkling 2 Small too large, the new model uses a looped transformer architecture with just 26B parameters, small enough to run on a laptop while still handling agentic workloads, scoring 20.1 on the AA Index.
The resharing account @AlexFinn hypes it as outperforming Qwen 3.8 27B in both speed and intelligence, claiming Thinking Machines has figured out how to fit significantly more intelligence into a much smaller model, and urges users to have their agents download and run it locally. The hype framing suggests the comparison should be verified against official benchmarks.
Related event: Thinking Machines Releases 26B Looped Transformer Inkling 2 Mini(72 posts)→
More from Models
- METR Q4: $90k of expert humans still can't beat frontier models, horizons hit 27h — iruletheworldmo · 2026-11-21
- Kaomoji as an emotion probe: Qwen3-8B's internal "happiness" is measurable — Sauers_ · 2026-11-21
- 27,262 thinking tokens, zero answer: Google auto-billed 23 empty Vertex AI crashes via HTTP 200 — Plenty-Jackfruit-218 · 2026-11-21
- Thinking Machines' new model claimed 5x faster than Qwen3.8, 15% more accurate — LiTianleli · 2026-11-21
- Gemini silently saves every Google search that gets an AI response, user finds — The-Neofighter · 2026-11-21
- Frontier Design Benchmark: Claude Fable 5.2 tops ranking, just 26 Elo below human designs — yuwen_lu_ · 2026-11-21