AI · November 21, 2026 · Moderate impact
Thinking Machines releases Inkling 2 Mini, an open looped model
Thinking Machines released Inkling 2 Mini, an open looped transformer in which 12 of its 24 layers run three times per token. The design lets the model reason internally for longer without generating extra text. On Artificial Analysis's Intelligence Index it ties with Qwen3.8 27B at roughly six times lower cost, and it is described as able to run on a laptop.
It shows a route to competitive open-weight reasoning on consumer hardware that does not depend on longer outputs.