Thinking Machines Lab's Inkling 2 Small is a 594B MoE model with 17B active parameters, live on Tinker with closed weights and an intended Apache 2.0 release after safety testing.
One 128 GB DGX Spark won't hold the 594B weights due next week, and DeepSeek's 552B model, out now, beats it on eight of the nine coding benchmarks they share.
Inkling from Thinking Machines is now available on AI Gateway, an open-weights multimodal Mixture-of-Experts model with a 1M token context window and controllable thinking effort.
Inkling-Small from Thinking Machines is now available on AI Gateway, an efficient open-weights multimodal Mixture-of-Experts model with a 1M token context window and controllable thinking effort.