Thinking Machines releases Inkling 2 Mini, a 26B looped transformer that runs on laptops
thinkymachines · x · 2026-11-21
Thinking Machines Lab released Inkling 2 Mini, a Mixture-of-Experts "looped transformer" with 26.4B total parameters (3.4B active): the middle layers run three times per token, letting the model reason more while writing fewer tokens — small enough to run on a laptop.
Key facts:
- Scores 20.1 on AA Index and leads all open-weights models under 100B total params on DeepSWE v1.1 (48.2%) and Vals Index v2.2 (46.5%), while decoding faster than similarly performing models
- The team also studied looping's impact on CoT monitorability and is shipping a variable-loop research model for community experiments
- Available via Tinker for inference and fine-tuning, with a model card on Hugging Face
More from Models
- Inkling 2 Mini runs on 32GB Macs via Ollama and on NVIDIA DGX Spark — thinkymachines · 2026-11-21
- Inkling 2 Mini architecture: 24 layers, with the middle 12 looped three times — thinkymachines · 2026-11-21
- Thinking Machines: more loop passes boost no-CoT capability without hurting monitorability — thinkymachines · 2026-11-21
- OpenAI emails API users 50% off new frontier model 6.2-Astra for 8 weeks — soumitrashukla9 · 2026-11-21
- Thinking Machines releases Inkling 2 Mini, a looped transformer topping sub-100B open-weights coding benchmarks — SonglinYang4 · 2026-11-21
- OnlyModels Model Fight 17: Qwen distills dominate, only 5/72 APEX claims held — Dave_Maynor · 2026-11-21