Thinking Machines' new model claimed 5x faster than Qwen3.8, 15% more accurate

LiTianleli · x · 2026-11-21

A widely shared take on @thinkymachines' new release (chart shows Inkling 2 Mini on DeepSWE v1.1): claimed 5x faster than Qwen3.8 while being 15% more accurate, and the 26B model is 12x faster than Ripple's 65B. The author argues this ends the debate on whether local models would depend on Chinese open-source releases, and makes local coding clearly tenable — "the frontier is moving onto your machine."

Original post →

More from Models

Models channel →