Enigmus

Enigmus

Private on-device LLM chat.

0 ratings
Free

Rating summary

Details

Released
May 28, 2026
Updated
November 1, 2026

Features

Enigmus video #1 for iPhone
Enigmus screenshot #2 for iPhone
Enigmus screenshot #3 for iPhone
Enigmus screenshot #4 for iPhone
Enigmus screenshot #5 for iPhone
Enigmus screenshot #6 for iPhone
Enigmus screenshot #7 for iPhone
iphone
ipad
🖼️Get Icon
Icons↘︎

About

Enigmus runs large language models entirely on your device. Conversations never leave your iPhone, iPad, or Mac — no accounts, no servers, no network required after the initial model download. Hardware requirements: iPhone 13 or newer (A15 Bionic or later), iPad with M1 chip or newer, or any Mac with Apple silicon. Devices without Metal 3 support are not compatible. Features • Ships with Qwen3.5-0.8B — chat within seconds of first launch, no download required. • Download additional open-weight models from Hugging Face: Google's Gemma 4 family (E2B up to 31B) and larger Qwen 3.5 / 3.6 variants, up to 122B on a Mac with the memory for it. The picker recommends models that fit your device's available memory. • Streaming responses with markdown, code-block, and typeset math rendering. • Reasoning-capable models - including the built-in Qwen3.5 - show their thinking before the final answer. • Local chat history backed by SwiftData - conversations stay on the device. • Adaptive layout for iPhone, iPad, and Mac, with keyboard and pointer support on the larger screens. • Customize tint color, fonts, and haptics in Settings. Privacy All inference runs through MLX, Apple's on-device machine-learning framework. No telemetry, no analytics, no account. The only outbound traffic is the optional model download from Hugging Face's public CDN.
Show more

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