webAI's 3.6B TwIL-LM3-Pro beats VibeThinker-3B by 35% on formal logic, runs locally in 2GiB
rohanpaul_ai · x · 2026-10-01
webAI released TwIL-LM3-Pro, a 3.66B-parameter open model built for local reasoning: the recommended Q4 build is a 2.09GiB file that runs via llama.cpp on CPU or local GPU, keeping private data on-device. It hit 500K downloads in its first month.
Key claims from webAI's evaluation:
- Highest recorded formal-logic score among small models compared, beating Weibo's VibeThinker-3B by 35%, Qwen3.5-4B by 24%, and Liquid AI's LFM2.5-8B-A1B by 47%
- SVAMP 95% and MuSR 64.1%, both tops among compared small models
- Built on IBM Granite with a 28% lift in formal-logic scoring
Related event: webAI releases open-source 3.6B local reasoning model TwIL-LM3-Pro(2 posts)→
More from Models
- Grokipedia v0.3 Hallucinates a Fake xAI Career for a Real User — NicoVerderosa · 2026-10-01
- Deedy: Trust Pricing, Not Benchmarks — High Price Means a Genuinely Strong Frontier Model — deedydas · 2026-10-01
- Benchmark score reports need 95% CI error bars, argues ML practitioner — rmcwhorter99 · 2026-10-01
- Gemini 4 Argon missed #1 on Vending-Bench due to memory slip on test end date — infoxiao · 2026-10-01
- Musician asks Suno and SoundCloud why its AI matched his private unreleased track — TheMoonMidas · 2026-10-01
- Early Gemini 4 Argon buzz cools as users flag poor token efficiency — adonis_singh · 2026-10-01