Get SoloLLM for iPhone and iPad.

SoloLLM is on the App Store as "SoloLLM: Private Offline AI", by Stephen Thorn. It runs on iPhone and iPad with iOS 17 or later.

One-time purchase. No subscription.

A voice conversation in SoloLLM: Qwen3.5 2B, on this device, writes a birthday message while the Speaking bar reads the reply aloud, with Stop Speaking and End buttons

Everything is included.

There are no in-app purchases. Every built-in model and every feature comes with the app.

16 built-in models

From Qwen3.5 0.8B to Gemma 4 12B, plus any GGUF model you add from Hugging Face, Files or a link.

See the models

Voice, Thinking and templates

Hands-free voice conversation, Thinking for models that support it, and 500 ready-made prompts and 67 templates for everyday jobs.

See the features

Tools and MCP

Web search when you choose, an on-device code sandbox, files, calendar and reminders, Agent mode that asks before sensitive steps, and MCP servers.

See the tools

From download to your first offline chat.

  1. Install SoloLLM from the App Store. The app itself is small; models download separately.
  2. Open it and pick a model. SoloLLM recommends one for your device's memory.
  3. Download the model once. Built-in models are about 500 MB to 6.5 GB.
  4. Chat. From now on it works without a connection. To make sure nothing goes online, turn on Offline only in Settings > Privacy & Data.
Requirements
DevicesiPhone and iPad
iOSiOS 17 or later
MemoryAbout 2B models on 4 GB iPhones, about 4B on 6 GB iPhones, Gemma 4 E4B on iPhone 15 Pro or later. Qwen3.5 9B and Gemma 4 12B on iPads with 12 GB or more.
AccountNone
PriceOne-time purchase. No subscription and no in-app purchases.

Private, offline AI on your iPhone.

Questions first? The FAQ covers memory, privacy and models.