Turn your Apple device into a private, local AI server. It hosts Large Language Models (LLMs) and offers an OpenAI-compatible API for development and testing. Run AI capabilities directly on your device without an internet connection.




249+ iOS apps curated and reviewed
Every iPhone needs a few good local llm server apps. We benchmark 249+ of them on App Store rating, freshness, and pricing, then surface the standouts so you don't have to scroll the App Store yourself.
| # | App | Price | Rating | Ads | In-App Purchases | Updated |
|---|---|---|---|---|---|---|
| 1 | Free | 3.7★ (3) | Yes | No | Jul 2026 | |
| 2 | Free | 4.6★ (5) | No | No | May 2026 | |
| 3 | Free | 3.6★ (9) | No | Yes | Aug 2026 | |
| 4 | $3.99 | — | No | No | Aug 2026 | |
| 5 | Free was $5.99 | 4.5★ (599) | No | No | Aug 2026 | |
| 6 | Free | 3.3★ (10) | No | No | Aug 2026 | |
| 7 | Free | — | No | Yes | Aug 2026 | |
| 8 | Free | — | No | No | Aug 2026 |




Turn your Apple device into a private, local AI server. It hosts Large Language Models (LLMs) and offers an OpenAI-compatible API for development and testing. Run AI capabilities directly on your device without an internet connection.



Connect your mobile device to large language models hosted on your computer. This app provides a secure and convenient way to access powerful AI capabilities on the go, bridging the gap between your phone and local LLM servers. Unleash your productivity with seamless interaction.




Run advanced language models directly on your iOS device with a privacy-first design. This app offers a user-friendly interface for easy setup and offline AI capabilities, supporting an Ollama-style API for compatibility with your preferred LLM UIs.




Access a wide range of AI language models, both locally on your device and through cloud APIs. This app allows you to chat with open-source models, connect to your own hosted LLMs, or utilize services like OpenRouter for broad model access.


This app allows you to chat with your own locally hosted AI models, offering a private and secure experience. It connects to Ollama or LM Studio servers on your local network, requiring some technical setup for a fully offline AI conversation.












This app provides a mobile interface for interacting with self-hosted large language models. It allows users to connect to their Ollama servers remotely, manage multiple chats, customize prompts, and adjust advanced model parameters for research and experimentation.












Connect to your Ollama models running on a local server or private endpoint directly from your iPhone. Enjoy fast, private chat with persistent history and file attachments, all stored locally on your device.



