# Introducing Inkling 2 Small

The 594B-parameter model is available on Tinker for inference and fine-tuning, with weights scheduled for Apache 2.0 release next week.

- Activates 17B parameters per token and includes a 292M-parameter vision encoder for image inputs.
- Pretrained across four phases on over 12.5 trillion tokens in native NVFP4 on NVIDIA GB300 NVL72 hardware.
- Trained via a joint reinforcement learning run over 1,075 steps and 17 million rollouts across coding, STEM, and agentic workflows.
- Scored 31 on the Artificial Analysis Intelligence Index and 1527 on AA-Briefcase for knowledge work tasks.

## Why it matters

Developers using Tinker get immediate access to a multimodal MoE model for agentic coding and research, with open weights arriving next week.

## Sources

- [Thinking Machines Lab: Introducing Inkling 2 Small](https://thinkingmachines.ai/news/inkling-2-small)

---

Summarized by dstilled on 2026-11-05. https://dstilled.ai/story/6287232a-0ec4-42fb-998f-a084fc2e03a1
