From the source
Thinking Machines Lab is introducing Inkling 2 Small, a Mixture-of-Experts model with 594B total parameters and 17B active, its second model generation, which supports image inputs and variable effort.
- The company says it far surpasses its previous models on the Artificial Analysis Intelligence Index with a score of 31, reflecting gains in agentic coding, vision, knowledge work and reasoning.
- Inkling 2 Small is initially available through Tinker with closed weights, and the company intends to release the full weights under an Apache 2.0 license next week after external safety testing and red-teaming.
- It can be tried on Tinker Playground today and is available for fine-tuning and sampling on Tinker, with checkpoints downloadable when the weights ship.
- The model was trained with RL on hundreds of thousands of long-horizon coding tasks, and early checkpoints were tested on OpenCode under the name Fledge-Alpha.
- In one autoresearch demonstration, it autonomously trained Qwen3.5-4B on Tinker for 4.5 hours at $426 in Tinker spend, more than doubling the model's forecasting score.
