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."
More from Models
- METR Q4: $90k of expert humans still can't beat frontier models, horizons hit 27h — iruletheworldmo · 2026-11-21
- Kaomoji as an emotion probe: Qwen3-8B's internal "happiness" is measurable — Sauers_ · 2026-11-21
- 27,262 thinking tokens, zero answer: Google auto-billed 23 empty Vertex AI crashes via HTTP 200 — Plenty-Jackfruit-218 · 2026-11-21
- Gemini silently saves every Google search that gets an AI response, user finds — The-Neofighter · 2026-11-21
- Frontier Design Benchmark: Claude Fable 5.2 tops ranking, just 26 Elo below human designs — yuwen_lu_ · 2026-11-21
- Hy4 Flash reads 1M tokens in 44 min on Mac Studio M3 Ultra, 81 min on DGX Spark — AIFlow_ML · 2026-11-21