Thinking Machines unveils Inkling, a 975B mixture-of-experts model with 1M-token context
Inkling packs 975 billion total parameters but only 41 billion active at inference, offers multimodal reasoning over text, images, audio, and a massive 1‑million‑token window. By releasing full weights and Tinker‑based fine‑tuning tools, Thinking Machines aims to make a versatile, customizable foundation model accessible for real‑world applications.