WebAI ships a powerful LLM that runs on your iPhone
WebAI has released TwiL-LM, a family of small formal-logic models designed for deductive reasoning tasks and built to run effectively on consumer hardware, particularly Macs and iPhones.
The 1.7 billion and 3 billion parameter models outperform much larger models on formal reasoning benchmarks and can run on consumer hardware, including iPhones.
Fast and private
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.
TwiL-LM excels at translating English into formal logic and is particularly useful for compliance rules, contract logic, and research reasoning.
Good as an expert model
“What’s surprised me most about TwiL is how useful it is beyond any single benchmark,” said David Stout, CEO and co-founder of webAI. “I use it every day for writing, tool calling, and general reasoning, but the more interesting capability is how well it works alongside other expert models.”
The AI is very small. Its recommended quantized build is just a 1.06 GB download that runs at roughly 367 tokens per second, fast enough for a small laptop or a phone.
Running AI at the edge is certainly on the wish list across regulated industries, such as healthcare, financial services, and pharmaceuticals where data cannot leave the device. Nothing is sent to an external cloud.
You can follow me on social media! Join me on BlueSky, LinkedIn, Mastodon and subscribe to The Core.
