Rohan Paul
@rohanpaul_ai
China's best small reasoning model (VibeThinker-3B) just got beaten by a 3.6B model from Austin.
> webAI's TwIL-LM3-Pro, a 3.66B local model, lifts IBM Granite's formal-logic score by 28%
> the recommended Q4 build is a 2.09GiB file that runs through llama.cpp on CPU or local GPU, so private data can stay on the device.
> TwIL-LM3-Pro now leads every small model webAI compared on formal logic, scoring roughly 35% above Weibo's VibeThinker-3B, 24% above Qwen3.5-4B and 47% above Liquid AI's LFM2.5-8B-A1B.
