LLM Server

LLM Server

LLM Server & API on your LAN

2 ratings
4 reviews
$19.99

Details

Released
May 1, 2026
Updated
November 19, 2026

Features

LLM Server screenshot #1 for iPhone
LLM Server screenshot #2 for iPhone
LLM Server screenshot #3 for iPhone
LLM Server screenshot #4 for iPhone
LLM Server screenshot #5 for iPhone
LLM Server screenshot #6 for iPhone
LLM Server screenshot #7 for iPhone
LLM Server screenshot #8 for iPhone
LLM Server screenshot #9 for iPhone
LLM Server screenshot #10 for iPhone
iphone
iphoneDuo
ipad
🖼️Get Icon
Icons↘︎

About

Transform your iPhone or iPad into a private AI inference server. Run large language, embedding, and image generation models locally. Expose OpenAI-compatible APIs to your network for seamless integration with browsers and other devices.

✓On-device AI model inference
✓OpenAI-compatible API
✓Web-based chat interface
✓On-device image generation
✓Local embedding model support
✓Offline operation
✓Hugging Face model integration
Show original description
+1

What's New in LLM Server

4.0.1

November 19, 2026

- Distributed inference (experimental, alpha): combine multiple iPhones and iPads on the same Wi-Fi to run one model together over RPC. Start the RPC Server card on the helper devices and offload model layers to them from the main device. - Reliability fixes.

More

User reviews

Server Performance Issue

I try to run any type of model and they type the first letter or first word, then it just stops. I disabled thinking and lowered quality settings yet nothing changed

Great for ai development

With this I can use the ipad as my local llm server, try different models, and use it for ai experiments. It supports tool calling and has nice dev features like proper logs, documentation, etc. And the app support is fast, friendly and useful. I am happy with it!

Missing image

Missing importing image on vision models, bought the app for that and it’s not working

Response from developer

The vision model feature is still being finalized and will land in the next update, coming very soon. If you bought the app specifically for this, email me at contact@linosec.com and I'll make sure you're looked after. Thanks for your patience.

Super simple et pratique

Vraiment convivial

Developer apps

FAQ

What is LLM Server?

LLM Server turns your iPhone or iPad into a private AI inference server. It allows you to run large language models, embedding models, and image generation models entirely on-device and expose OpenAI-compatible APIs to your local network.

Does LLM Server have ads?

No, LLM Server does not contain advertisements. It is a paid application designed for a seamless, ad-free user experience.

What devices does LLM Server support?

LLM Server is supported on iPhone and iPad devices. It requires iOS 17 or later and utilizes Apple Metal GPU for inference.

How much does LLM Server cost?

LLM Server is a paid application priced at $19.99. There are no subscriptions or in-app purchases mentioned.

Can I use LLM Server offline?

Yes, LLM Server is fully offline. Once a GGUF model is downloaded, inference runs locally on your device with no internet connection required, making it suitable for airplane mode.

What kind of AI models can I run with LLM Server?

You can run any GGUF model from Hugging Face, including LLaMA, Mistral, Phi, Gemma, Qwen, DeepSeek, embedding models, and Stable Diffusion image models. You can browse and download directly within the app or import your own files.

How secure is LLM Server?

LLM Server offers enterprise-grade security with TLS/HTTPS encryption, API key authentication, and bind control to manage network access. Your data and prompts remain entirely on your hardware.

How often is LLM Server updated?

The latest version of LLM Server is 3.1.7, last updated on November 11, 2026. This indicates a recent update, suggesting ongoing development and support.