Inkling-Small Released: 276B Parameter MoE Model

simonguozirui · x · 2026-07-31

Thinkymachines has released Inkling-Small, a Mixture-of-Experts (MoE) model with 276B total parameters and 12B active parameters. It features a 1M token context window, variable thinking effort, and native image and audio understanding.

The developers claim it achieves performance comparable to the larger Inkling model at a quarter of the size, with full weights openly available. Users can fine-tune it on Tinker or interact with it in the Tinker Playground. Modal has announced Day 0 support, noting that its NVFP4 checkpoint fits on a single NVIDIA B300 GPU.

Related event: Thinking Machines Releases Inkling-Small Open-Source Model(23 posts)→

Original post →

More from Models

Models channel →