Thinking Machines releases Inkling-Small open-weights MoE model

Inkling-Small is a 276B-total, 12B-active Mixture-of-Experts model, about a quarter the size of Inkling (975B/41B), trained on NVIDIA GB300 NVL72 systems. It scores 31.6% on Humanity's Last Exam, beating Inkling's 29.7%, and 64.7 on Terminal-Bench 2.1 vs 63.8. Full weights are available on Hugging Face, with support in transformers, SGLang, vLLM, and llama.cpp.

Featured · Mira Murati