Thinking Machines releases Inkling 2 Small, a 594B-total MoE model
AIThinking Machines released Inkling 2 Small, a 594B-total, 17B-active multimodal mixture-of-experts model, available now on Tinker. Its Apache 2.0 weights are promised for next week after external safety testing, and Artificial Analysis scored it 31 on its Intelligence Index.
Loading source posts…
Source details
Latent Space · swyx .ai · latent.spacePublished · added here
Original title: [AINews] Inkling 2 Small: 17A-594B trained in 68 hours on 12T tokens, beating Muse Spark