privateSLM: Local AI Chat
Offline AI experts. Pay once.
About
This AI chat application runs entirely on your device, ensuring complete privacy with no cloud reliance or data leaving your phone. It offers smart engine integration and robust chat management features for seamless, offline use.
What's New in privateSLM
2.2.0
July 17, 2026
This release is a full native rewrite — faster, lighter, and more private. • Expert models by category: coding, math, medical, legal, finance, translation, mental-health, plus fast general chat. • Model catalog matched to your iPhone's memory, checked on-device. • Big 7B expert models now fit in memory reliably. • Full chat history, voice input and spoken replies. • Edit, regenerate, stop and copy replies; adjustable prompt & sampling. • Uses Apple Intelligence on supported devices.
MoreDeveloper apps
FAQ
Does privateSLM have ads?
Yes, privateSLM contains advertisements. This is indicated by the 'hasAds' flag in its data.
What is the price of privateSLM?
privateSLM is a one-time purchase priced at $4.99. There are no subscriptions or hidden costs.
How often is privateSLM updated?
The latest version, 2.0.1, was released on 2026-07-05. Update frequency is not explicitly detailed but the app is actively maintained.
What devices does privateSLM support?
privateSLM is available on iPhone, iPad, and Mac, with a layout that adapts to larger screens.
Is privateSLM suitable for children?
privateSLM has an age rating of 4+, making it suitable for younger users. The app focuses on privacy and on-device processing.
Can I use privateSLM without an internet connection?
Yes, privateSLM is designed to work 100% offline. Airplane mode is fully supported, and no internet connection is required for its operation.
How does privateSLM manage chat history?
privateSLM allows for full chat history management, including searching, renaming, and deleting multiple conversations. Users can also edit messages and regenerate replies.
What makes privateSLM's engine selection smart?
On compatible Apple devices, it uses Apple's built-in system model running on the Neural Engine. On other devices, it allows users to download and run fast, open models locally.
