Thinking Machines Lab Releases Inkling-Small: A 276B Total, 12B Active Open Weights Multimodal MoE Model

1Key Takeaways

• Inkling-Small matches Inkling at a quarter the size, and its NVFP4 checkpoint runs on one NVIDIA B300 GPU.
• Headline: Thinking Machines Lab Releases Inkling-Small: A 276B Total, 12B Active Open Weights Multimodal MoE Model
• Category focus: AI Models — relevant for AI builders and decision-makers.