
Enigmus
Private on-device LLM chat.
About
What's New in Enigmus
1.3.0
November 1, 2026
Enigmus can now serve its model to other apps. Turn on the LLM Server and coding tools, scripts and chat apps reach it through an OpenAI-compatible API, with a web chat served from the app itself - still entirely on your device. Also in this release: • Reach it from other devices on your Wi-Fi with Allow Network Access, by address or QR code. Off by default. • Tool calls on Qwen 3.5 and 3.6 models from 2B up, marked with a wrench on the install screen. • A live request log, with prompts kept out of it unless you choose to show them. • Message text follows your system text size; adjust it in Settings on iPhone and iPad, or with ⌘+ and ⌘− on Mac. • Re-benchmark any installed model from the models list. • A clearer thinking toggle, and a model picker that closes once your model has loaded.
More





