This app provides a private AI chat experience that runs entirely on your device, no internet required. It offers a catalog of open-source AI models and features like document analysis, daily briefings, and mini-apps within chats. Enjoy true privacy with no accounts or tracking.
1.45
September 4, 2026
Fixes for reliability and first-run setup. • A paused download now reconnects to the right model when you reopen the app, instead of showing a progress screen that never moves. • If you already have models installed, the app no longer asks you to pick one while it is still loading. • Choosing "Decide later" during setup now installs the recommended starter model, so you land in a working chat.
MoreUnlimited models, chats & custom system prompts
$19.99
Lifetime Pro
Unlock all Pro features. Pay once, own forever.
OnDevice LLM is a mobile application that allows you to run powerful AI models entirely on your iPhone or iPad. It operates 100% offline, meaning no internet connection or account is required for its core functionality.
No, OnDevice LLM does not contain advertisements. The app is designed for a private and uninterrupted user experience, with no tracking SDKs or analytics reporting your prompts.
The app features a curated catalog of top open-source models, including Gemma, Llama 3.2, Qwen 2.5, Phi-4 Mini, SmolLM2, DeepSeek R1, and Ternary Bonsai models for Apple Silicon.
Privacy is central to OnDevice LLM. All conversations, memories, and downloaded models are stored exclusively within your device's app sandbox. Your data never leaves your phone, ensuring no logging or mining by any company.
The Pro upgrade offers unlimited model loading and saved chats, along with custom system prompts and the ability to add custom HuggingFace model URLs. This is available as a one-time lifetime purchase.
Yes, you can attach PDFs, images, or text documents directly to your chats. The AI will read and process these local files to provide relevant responses.
The 'Brief my day' feature combines your device's Calendar and Reminders with the app's private memory to generate a personalized morning briefing, all processed securely on your device.
OnDevice LLM is available for both iPhone and iPad devices, running on Apple Silicon for optimized performance.
