FrontierThe story, in brief
Thinking Machines Lab Releases Inkling-Small: A 276B Total, 12B Active Open Weights Multimodal MoE Model
276B parameters, 12B active—Thinking Machines Lab's Inkling-Small matches its flagship at a quarter the size and fits on a single B300.
The KeyNews take
Why it matters
Open-weight MoE efficiency milestone: a multimodal model achieving parity with a larger peer via sparsity and quantization, lowering the bar for practitioners to run capable models on consumer/mid-tier hardware.
The key facts
7 to knowInkling-Small: 276B total parameters, 12B active (MoE sparse)
Multimodal (vision + language) capability
Matches Inkling (full-size version) performance at 1/4 scale
NVFP4 quantization checkpoint
Runs on single NVIDIA B300 GPU
Open weights release
Published: August 2, 2026
Go to the source
MarkTechPostmarktechpost.com
Publisher excerpt: Inkling-Small matches Inkling at a quarter the size, and its NVFP4 checkpoint runs on one NVIDIA B300 GPU