
A model that can see and refine what it builds
Inkling 2 Small is Thinking Machines Lab's new 594B-parameter MoE model with 17B active, built for long-horizon coding, visual tasks, and agents. Available on Tinker for inference and fine-tuning.
Inkling 2 Small is a 594 billion-parameter mixture of experts (MoE) model designed for long-horizon coding and visual tasks, with 17 billion active parameters. It is available on Tinker for inference and fine-tuning.
A source that found nothing is a measurement. A source that has not run is a gap. Neither means the launch lacks the thing.