TwiL-LM3

webAI

A 3B formal-logic reasoning model built from SmolLM3-3B by LoRA fine-tuning, checkpoint fusion, WiSE-FT interpolation and entropy-weighted GRPO, which beats gpt-oss-120b on four of five lanes of webAI's formal-reasoning suite.

Specs

Model

Family
TwiL-LM
Variant
3B
Parameters
3B
Weights
Open
License
webAI Non-Commercial License v1.0

Limits

Context
65,536 tokens

Modalities

Input
Text
Output
Text

Capabilities

Reasoning
Yes

Dates

Released
7 Aug 2026
webAI

webAI Releases TwiL-LM, a Family of Formal-Logic Models That Outreason a 120B Model and Run on an iPhone

Built for compliance rules, contract logic, and research reasoning, the 3B model beats OpenAI's open-weights gpt-oss-120b, a model 40× its size, on four of five formal-reasoning benchmarks, while the 1-gigabyte 1.7B variant outperforms every sub-2B model webAI evaluated.

webAI Team
webai.com

More from webAI

All models

TwiL-LM 1.7B

webAI

A LoRA adapter over SmolLM2-1.7B-Instruct for formal logic — FOL translation, entailment, semantic parsing and Lean assistance — quantized to a 1.06 GB download that runs on a phone.

webAI Non-Commercial License v1.06d ago

Keep up with the tools

An occasional email when notable AI dev tools and models land in the directory. No spam, unsubscribe anytime.