# MLXHub: Local AI & LLM Server — On-device LLM, OpenAI API

> On-device LLM, OpenAI API (iPhone/iPad app by Juan Colilla.)

- Source: https://appshunter.io/ios/app/mlxhub-local-ai-and-llm-server/id6766485144 (this page in markdown: same URL + `.md`)
- Developer: [Juan Colilla](https://appshunter.io/developer/1526484935)
- Category: Developer Tools, Productivity
- Price: Free
- Age rating: 9+
- Requires: iOS 26.0 · 48 MB
- Languages: American English, French (France), German (Germany), Hindi, Japanese, Russian, Chinese (Simplified, China), European Spanish
- Released: 2026-07-14
- Data updated: 2026-08-22
- User reviews in markdown: https://appshunter.io/ios/app/mlxhub-local-ai-and-llm-server/id6766485144/reviews.md

## What is MLXHub?

Run AI locally. Your device. Your data.

MLXHub brings open-source language models to iPhone and iPad, powered by Apple Silicon and the mlx-swift inference engine. No cloud. No data leaves your device.

Chat with powerful models
Download and run LLMs and vision-language models (VLMs) directly on your device. Send text messages or attach photos — the model sees and responds without touching any server.

Apple Intelligence built in
On supported devices (iPhone 15 Pro / 16 and later with Apple Intelligence enabled), use Apple's on-device model for instant, private responses alongside any downloaded model.

Your personality, your assistant
Set a global Agent Personality to define the AI's tone and style. Override it per-conversation with custom system instructions. No prompt engineering needed — just describe what you want.

Browse and install models
Explore a curated catalog of optimized models — from tiny 0.6B models that fit in under 1 GB to powerful 7B models for deeper reasoning. Color-coded RAM badges tell you at a glance whether a model fits your device. Search HuggingFace directly to install any compatible model.

Local LAN server
Turn your iPhone or iPad into a portable, OpenAI-compatible inference endpoint on your local network. MLXHub's optional LAN server exposes /v1/chat/completions so any app — from a Mac running Continue.dev to a custom script — can use your device's models. No internet required. Auth-protected. Bonjour-discoverable.

Built for Apple Silicon
MLXHub uses mlx-swift, Apple's own machine-learning framework, to run models at full Metal GPU speed. Model weights are quantized (4-bit, 8-bit) for the best quality-per-GB ratio on iPhone and iPad hardware.

Privacy first
No analytics. No tracking. No ads. No account required. Model inference never leaves your device. The optional LAN server only listens on your local network and is off by default.

Terms of Use (EULA): https://www.apple.com/legal/internet-services/itunes/dev/stdeula/


## Version history (last 5 releases)

### 1.1.1 — 2026-08-08

Fixed a bug that prevented setting whether a model should reason or not via the LAN server.

### 1.1.0 — 2026-08-01

MLXHub now has a more refined visual experience throughout the app, with new activity orbs, improved contrast, and theme color options for Plus.

We also polished animations and transitions so chat, models, and the LAN server feel smoother. This update improves performance and responsiveness during generation, scrolling, and server use.

### 1.0.4 — 2026-07-22

Open MLX models directly from Hugging Face.

Tap MLXHub on a compatible Hugging Face model page to open its details in the app and download it. If MLXHub isn’t installed, you’ll be taken to the App Store.

### 1.0.3 — 2026-07-17

Fixed the LAN server port field: you can now type any port number without it jumping to another value on its own.

Also fixed the keyboard getting stuck open with no way to dismiss it on several settings screens — swipe the list or tap Done to close it.

### 1.0.1 — 2026-07-15

MLXHub expands compatibility with 1-bit quantized MLX models, including Bonsai 27B.

This update integrates new versions of mlx-swift and mlx-swift-lm to load and run these models directly on your device.

## Apps similar to MLXHub

| App | Rating | Price | Category |
| --- | --- | --- | --- |
| [Difftray: Code Review & Diff](https://appshunter.io/ios/app/difftray-code-review-and-diff/id6789255782) | — | Free | Developer Tools |
| [Skycape](https://appshunter.io/ios/app/skycape/id6758614126) | 1.0 (1) | Free | Developer Tools |
| [Price Localize - AutoPricing](https://appshunter.io/ios/app/price-localize-autopricing/id6746580211) | — | Free | Developer Tools |
| [Orange Cloud for Cloudflare](https://appshunter.io/ios/app/orange-cloud-for-cloudflare/id6779323783) | 3.4 (5) | Free | Developer Tools |
| [Visual Code Editor - vCode](https://appshunter.io/ios/app/visual-code-editor-vcode/id6789877680) | 5.0 (3) | Free | Developer Tools |
| [NativeX — On-Device AI Lab](https://appshunter.io/ios/app/nativex-on-device-ai-lab/id6788332112) | — | Free | Developer Tools |

## More apps by Juan Colilla

- [agendy: Contact Cleaner](https://appshunter.io/ios/app/agendy-contact-cleaner/id6747459084)
- [Poolendar](https://appshunter.io/ios/app/poolendar/id6757929768)

All apps by Juan Colilla: https://appshunter.io/developer/1526484935

## Related topics

[llm server](https://appshunter.io/ios/topics/llm-server) · [mserveur](https://appshunter.io/ios/topics/mserveur) · [local llm server pro](https://appshunter.io/ios/topics/local-llm-server-pro) · [llm hub](https://appshunter.io/ios/topics/llm-hub) · [metricool software sl](https://appshunter.io/ios/topics/metricool-software-sl) · [local llm server](https://appshunter.io/ios/topics/local-llm-server)

---

*Data collected daily from the US App Store and indexed by [AppsHunter](https://appshunter.io/). User reviews are verbatim App Store reviews. Ratings, prices and chart positions refresh continuously; this snapshot is from 2026-08-22.*