Thinking Machines launches Inkling 2 Small: 594B-param MoE with 17B active, AA index 31
FinanceYF5 · x · 2026-11-09
Thinking Machines introduced its second-gen model Inkling 2 Small, a Mixture-of-Experts model with 594B total parameters and 17B active, supporting image inputs and variable effort.
- Scores 31 on the Artificial Analysis Intelligence Index, far surpassing its first-generation models, driven by more efficient pre-training and a large unified RL run
- Strong at long-horizon autonomous work: iteratively builds and refines websites, games, and 3D designs from visual feedback; demos include a procedurally generated Three.js city simulator and a from-scratch Python PC emulator that boots real Linux
- Available now on Tinker with closed weights (inference and fine-tuning); full weights planned under Apache 2.0 next week after external safety testing and red-teaming
Related event: Thinking Machines Releases Inkling 2 Small with Open Weights Coming(3 posts)→
More from Models
- Together AI: leaderboards are for shortlisting, your production traffic is the real benchmark — togethercompute · 2026-11-09
- Gemini quietly reads your Android messages, calls and Gmail — here's how to limit it — Med1_Ai · 2026-11-09
- Airbnb: fine-tuned small model matches frontier quality on production classifiers at ~1% of the cost — lak_luster · 2026-11-09
- Kaggle team position paper: AI competitions are the gold standard for GenAI evaluation — MeganRisdal · 2026-11-09
- Internal 32B/122B/256B checkpoints rumor debunked as AI-generated fake news — teortaxesTex · 2026-11-09
- Joseph Jacks: Liquid AI is the only US frontier lab keeping open weights ahead of China — JosephJacks_ · 2026-11-09