# LM Mini: Private Offline AI — AI Chat for Ollama & LM Studio

> Mobile interface for local AI models via Ollama, LM Studio, and on-device execution. (iPhone/iPad app by Sultan Haider.)

- Source: https://appshunter.io/ios/app/lm-mini-private-offline-ai/id6751125309 (this page in markdown: same URL + `.md`)
- Developer: [Sultan Haider](https://appshunter.io/developer/1669774421)
- Category: Productivity, Utilities
- Price: Free with in-app purchases
- Rating: 4.40/5 from 163 App Store ratings · 54 written reviews indexed
- Age rating: 4+
- Requires: iOS 16.0 · 173 MB
- Languages: American English
- Released: 2025-09-20
- Data updated: 2026-11-14
- Monetization: freemium
- User reviews in markdown: https://appshunter.io/ios/app/lm-mini-private-offline-ai/id6751125309/reviews.md

## What is LM Mini?

Chat with LM Studio, Ollama, and oMLX from your iPhone — or run on-device models offline. Private local AI on hardware you control. No cloud chat subscription required.

THREE WAYS TO USE IT

1. On-device — download a model and chat with no internet
2. Connected — LM Studio, Ollama, Jan AI, or oMLX over Wi‑Fi or USB
3. Remote — LM Mini Connect from anywhere, encrypted with your key

One app for phone-side models and your desktop local setup.

WHAT TO EXPECT

Phone models are not the same as huge hosted models in a data center. They are smaller, and that is expected. Performance will vary by hardware.

What you gain is control: offline use, private chats on your device or your home machine, and freedom to run the open models you choose.

BUILT FOR

- People already running LM Studio, Ollama, oMLX or Jan AI who want that stack in their pocket
- People who want on-device chat when they are offline or away from Wi-Fi
- People who care about keeping conversations off third-party chat servers
- Researchers, builders, and privacy-minded users experimenting with local AI

INSIDE THE APP

- Download and run on-device models on your phone
- Connect to LM Studio, Ollama, Jan AI and oMLX
- Remote access through LM Mini Connect with your encryption key
- Manage and download models on LM Studio from your phone

- Local conversation history, folders, and context usage tracking
- Personas, plus group chat with up to 5 models in one conversation
- Voice chat with Kokoro
- Image generation with ComfyUI and Automatic1111
- Web search through SearXNG
- Memory so your AI can remember details about you
- On-device semantic search across your chats
- Background generation, so you don't have to sit and stare at the screen
- Themes, backgrounds, and avatars
- Import chats from LM Studio
- Optional encrypted cloud backups
- Custom servers with custom headers
- Optional APIs when you want them: OpenAI, OpenRouter, Mistral, DeepSeek, Google Gemini, and more
- MCP tool calling
- In-app support and feature requests
- Dark mode and a chat UI meant for daily use

PRIVACY

For local use, chats stay on your phone, or between your phone and your own computer. We don't need your conversations to make that core local path work. If you choose optional cloud APIs, those requests go to the provider you pick.

SETUP

On-device: a compatible phone with enough free storage and memory for the model you pick. Connected mode: LM Studio, Ollama, or oMLX on your computer, plus local network or USB access, or LM Mini Connect for remote use.

Install LM Mini and keep your local AI with you.

Download LM Mini today and start chatting with your local AI models privately and securely!

This app uses Apple Standard EULA license and its available at https://www.apple.com/legal/internet-services/itunes/dev/stdeula/

## Key features

- On-device model execution
- Connect to LM Studio/Ollama
- Remote access via LM Mini Connect
- Voice chat and image generation
- Web search integration
- Local conversation history and management
- Optional cloud backups

## Pricing and in-app purchases

Base price: Free.

**Subscriptions**

| Subscription | Price | Period |
| --- | --- | --- |
| Yearly Subscription | $29.99 | per year |
| Monthly Subscription | $4.99 | per month |

**One-time purchases**

| Purchase | Price | Type |
| --- | --- | --- |
| Lifetime Premium | $119.99 | one-time |


## Is LM Mini safe?

LM Mini: Private Offline AI appears safe based on user ratings. The AppsHunter Safety Score for LM Mini is 86 out of 100. This assessment is based on 163 user ratings, with an App Store average of 4.4 out of 5. Of 163 App Store ratings, 85.3% point to a safe experience, 3.7% suggest some concerns, and 11.0% point to a risky experience.

## Is LM Mini legit?

LM Mini: Private Offline AI appears to be a legitimate app. The AppsHunter Legitimacy Score for LM Mini is 83 out of 100 points across 7 verification signals from App Store and developer data.

## Recent user reviews (10 of 54)

All indexed reviews: https://appshunter.io/ios/app/lm-mini-private-offline-ai/id6751125309/reviews.md

### 1/5 — Locking model access behind a paywall goes too far

*2026-11-07*

I understand charging for extra features, but putting access to freely available models like Gemma 4 12B behind a paywall goes too far. Simply using a model on my own hardware shouldn’t require a paid upgrade. Charge for added functionality, but let users choose which models they run. Sorry but 1 star from me

### 1/5 — This version is borked

*2026-11-05*

The bots messages are hidden (bug), you can only see the reasoning/thinking in a popup box when you press "edit" on the bots answer. Literally not working, can't see the actual response, just that. Thanks anyways, it worked great. EDIT 5.11.2026: Looks like the chats are being spied on, my witty nick gets censored and thinking/reasoning vanished w/o a trace in the GUI. Yet another loser dev scared of me! /shrugs Use the alternatives, people. The uncensored alternatives.

### 2/5 — Not great

*2026-10-28*

The app works sometimes. It kind of runs models it can access. They stall out more than they work. On top of that  the MLX folder import function is completely broken. If this worked as advertised instead of throwing errors and doing nothing else, this would be a 5 star review.

**Developer response:** You are right, it was broken and I have fixed & pushed a new version for it. Please update. If there are any other issues, there is an active support section under settings, I'll be really happy to quickly resolve the issues you face.

### 2/5 — Wenn es funktionieren würde…

*2026-10-20*

Die Idee ist gut. Dafür 2 Sterne. Ich entwickle aber lieber meine eigene Lösung weiter, da LM Mini selbst mit den kleinsten Modellen auf dem iPhone 15Pro abstürzt. Erst sollte eine App funktionieren bevor man sogar eine Pro-Version anbietet. Soll mit der App nur Geld verdient werden oder auch etwas geleistet werden? Echt schade.

**Developer response:** Falls es zu einem Absturz kommt, melde dies bitte unter „Einstellungen“ -> „Support“ – ich werde mich dann schnellstmöglich darum kümmern. Da die App zudem Open Source ist, kannst du den Fehler bei Bedarf auch selbst beheben. Mein Ziel ist es, den Großteil der App kostenlos anzubieten. Es wäre sehr hilfreich, wenn du ein Ticket mit weiteren Details zum Absturz erstellen würdest, damit ich diesen nachvollziehen kann. Vielen Dank!

### 5/5 — Solid app!

*2026-10-20*

Works flawlessly with my local LM Studio server. Really cool also being able to load up and play with small models right on-device as well.

Highly recommend enabling “Low battery mode” under “Appearance”
in the settings, as at least on my iPhone 15 Pro Max using it with that off and the “glass effects” enabled drains the battery like I’m running a full 3D game just chatting with a model on my local server! Swapping those toggles made a night and day difference.

I don’t mind being limited to manually loading a single local model on the free version, but please please please let us do the same single manual load with an mlx model!

**Developer response:** Thank you, I am glad you liked it. I'll add MLX model too, you can import MLX from Files app too. If you have more suggestion please user Support and Feature Request under Settings.

### 1/5 — Stopped working after updates

*2026-09-26*

This app used to work perfectly fine on my iPhone 8 Plus running iOS 16.7.16. I've had it since July, but it now immediately crashes after showing the splash screen.

I've already tried reinstalling the app, clearing its data, restarting my phone, and removing my LM Studio models. I have plenty of free storage (~25 GB), and the freshly installed app only shows 283 KB of Documents & Data.

I'm currently on LM Mini 1.9.10. I didn't manually update it, so I suspect an automatic update may have introduced an incompatibility with older iPhones/iOS 16. Please look into this, because the app previously worked on this exact device.

**Developer response:** Edit: Did it work for you with v.19.12?
I am guessing here from your message (appreciate the details), It might be from new changes released in v1.9.10 for on-device Inference, I have applied and uploaded a fix for it in v1.9.12 which is already queued up for a review by Apple and should be available to download soon. Let me know how it goes.

### 1/5 — Quickly jammed with garbage

*2026-08-10*

I was using this app as a super simple front end to lmstudio server, it seemed to be one of the better apps for that purpose. I put it down for a couple weeks and come back and it’s now jammed with subscription prompts in every corner and a bunch of unnecessary features like personas used to upsell the subscription. They take up space and can’t be hidden if you just want basic usage.

Unfortunately in the age of llm coded apps it’s all too easy to ruin the experience chasing money. Someone should make an app that can be bought once that just chats against lm studio/completions api. They’d have at least one purchase right here!

**Developer response:** Whole LM Studio Completion AI is free feature. You don't even need a single purchase for it. Persona is just an easier name for System Prompt and its free feature too. If you are facing an issue with something there is a very active Human Support under Settings. I'd be really happy to help you have the experience you want from the app.

### 5/5 — The Developer seals the deal

*2026-07-23, version 1.8.2*

This app isn't the "perfect" LM Studio app, and there's definitely room for improvement, but let me tell you why I actually pay for Pro.

The developer actually cares.

He responds to feature requests, bug reports, and doesn't spent months between updates.  You can tell this is a passion project by the regular and meaningful updates.  Sure there's some bugs here or there, sure some things could be added, but as of this writing (July 22 2026), you won't find a better value, better compatibility, better communication or overall better experience on a native iOS app.  Trust me I've looked.  

I use mostly local LLMs via ollama initially and LMStudio after, and now use open router as well.  This app handles them all better than any other.

Even on just the free version,  this app as of this writing is 10x better than Locally (LM Studio's official app).

The fact that it has speech, TTS, and photo llm handling for both on-model and via remote-local in addition to cloud providers is incredible.

### 5/5 — How LMS client should look like

*2026-07-22*

That’s a powerful tool to use with LM Studio. Active development in progress. Kudos to author. I want to see more improvements to  image generation with ComfyUI and I’ll definitely buy PRO version, as it became my work-on-the-couch favorite.

**Developer response:** Thank you, your positive feedback keeps me going. Please do not hesitate to post requests in the Feature Request and support section about Image generation, I'll try to fulfill as many as humanly possible.

### 1/5 — New chat Clutter

*2026-07-22*

Opening a new chat has an extreme excess overflow of screen clutter for no actual reason. I am unable to close my keyboard since I can’t tap on the once empty space to see if there are spelling mistakes or errors due to this annoyance. Please remove the useless scrolling prompts upon new chat creation or at least a toggle to remove them. (They completely erase and rewrite the prompt if they are tapped, even by accident making them a bane.)

**Developer response:** This is now fixed in v 1.8.3 and also I have added a toggle under Settings -> Appearances -> New Chat Suggestions. You can turn it off to have cleaner new chat.

## Frequently asked questions about LM Mini

### What is LM Mini?

LM Mini is a mobile application that allows you to chat with local AI models, including those from LM Studio and Ollama, or run models directly on your device. It provides private, local AI experiences without requiring cloud subscriptions.

### How does LM Mini handle privacy?

For local use, your chats remain on your phone or between your phone and your computer. The app does not require access to your conversations for its core local functionality. If you opt for optional cloud APIs, requests are sent to your chosen provider.

### Can I use LM Mini offline?

Yes, LM Mini supports on-device model execution, allowing you to chat with AI models without an internet connection. You can download compatible models and use them directly from your phone.

### What are the subscription options for LM Mini?

LM Mini offers a monthly subscription for $4.99 and a yearly subscription for $29.99. These subscriptions likely unlock premium features or enhance the user experience beyond the free tier.

### What devices is LM Mini compatible with?

LM Mini is available on Mac, Apple Watch, iPhone, and iPad, offering a versatile experience across Apple's ecosystem. This allows for seamless integration with your existing devices.

### How often is LM Mini updated?

The latest version of LM Mini is 1.10.10, and it was last updated on November 5, 2026. This indicates a recent update, suggesting ongoing development and support for the application.

### What is the age rating for LM Mini?

LM Mini has an age rating of 4+, making it suitable for a wide range of users. This rating suggests that the content within the app is generally appropriate for children and adults.

### Does LM Mini offer image generation?

Yes, LM Mini supports image generation through integrations with ComfyUI and Automatic1111. This feature allows users to create images directly within the app using their local AI models.

## Version history (last 5 releases)

### 1.10.11 — 2026-11-14

Adds option to enable/disable Preserve thinking.
Quality of life improvements.

### 1.10.10 — 2026-11-05

- Behoben: Import eines MLX-Modellordners schlug bei Ordnern außerhalb der App fehl
- Du kannst jetzt mit jedem Tarif ein eigenes Modell (GGUF oder MLX) importieren
- Behoben: Pro blieb nach dem Kauf gesperrt, bis die App neu gestartet wurde
- Alle Upgrade-Dialoge zeigen jetzt denselben günstigsten Preis in deiner Landeswährung
- Behoben: Der Monatspreis wurde außerhalb der USA in US-Dollar angezeigt
- Behoben: „Foto aufnehmen“ im Anhang-Menü stürzte manchmal ab
- Verbesserte chinesische Übersetzung

### 1.10.8 — 2026-11-02

- Added About you in Settings: your name and a few words about yourself, sent with every chat so you don't have to introduce yourself
- Added: choose how the AI writes image prompts for each image server (ComfyUI, A1111, on-device), for example natural sentences for Flux or Krea
- Fixes LM Studio chats failing with "not found" on some servers
- Fixes Unsloth loading or downloading Q4_K_M instead of the quant you picked
- Fixes broken MLX Import from Files App

### 1.10.7 — 2026-10-25

- Added a direct Wi-Fi connection to your Mac when you're on the same network: faster, encrypted, and works without internet
- Added: pick any model downloaded on your Mac from your phone
- Improved chat sync with your Mac: only changes are sent, pictures and memories come along, and edits and deletions sync
- Fixes chats with your Mac's models failing when Tool Use is off, in group chats and in Arena
- Fixes big models on your Mac timing out while they load
- Improved messages when your Mac is loading, needs a new QR scan or needs an update

### 1.10.5 — 2026-10-24

- Improved on-device thinking models like Qwen 3.5: their thinking now goes in the collapsed thoughts section, and you can turn Think off
- Improved iCloud sync: only chats that changed are uploaded, so it's much lighter on your phone
- Fixes the chat list and the open chat getting stuck loading until you restart the app
- Fixes deleted chats and empty New Chats coming back with iCloud sync
- Fixes the chat still moving while a reply is written when "Follow new replies" is off
- Fixes large models failing to load over Remote Access with server error 524
- Fixes the Persona Generator and the News widget using LM Studio instead of Ollama, cloud providers or Apple Intelligence
- Fixes image generation failing on Automatic1111 after loading a ComfyUI workflow
- Fixes Ollama replies that stall mid-way being lost; the text already written is kept, with the reason
- Fixes Pro Search showing "temporarily unavailable" when LM Studio blocks per-request MCPs; you now see which setting to turn on
- Fixes servers that aren't LM Studio showing "Endpoint not found"; you now see how to add them instead

## Apps similar to LM Mini

| App | Rating | Price | Category |
| --- | --- | --- | --- |
| [Locally AI by LM Studio](https://appshunter.io/ios/app/locally-ai-by-lm-studio/id6741426692) | 4.7 (1,980) | Free | Productivity |
| [Enclave - Local AI Assistant](https://appshunter.io/ios/app/enclave-local-ai-assistant/id6476614556) | 4.7 (1,129) | Free | Productivity |
| [Pal Chat - AI Chat Client](https://appshunter.io/ios/app/pal-chat-ai-chat-client/id6447545085) | 4.3 (440) | Free | Productivity |
| [MLC Chat](https://appshunter.io/ios/app/mlc-chat/id6448482937) | 4.2 (83) | Free | Productivity |
| [Local LLM: MITHRIL](https://appshunter.io/ios/app/local-llm-mithril/id6751945393) | 4.3 (18) | Free | Productivity |
| [Noema: Local AI & Offline LLM](https://appshunter.io/ios/app/noema-local-ai-and-offline-llm/id6751169935) | 4.6 (40) | Free | Productivity |

## More apps by Sultan Haider

- [Photo Print PK](https://appshunter.io/ios/app/photo-print-pk/id1669774419)
- [LaShareek](https://appshunter.io/ios/app/lashareek/id6741438403)
- [Receipts AI: Expense Tracker](https://appshunter.io/ios/app/receipts-ai-expense-tracker/id6756528405)
- [Tabeer — AI Dream Journal](https://appshunter.io/ios/app/tabeer-ai-dream-journal/id6760970817)
- [ComfyUI Mini: Stable Diffusion](https://appshunter.io/ios/app/comfyui-mini-stable-diffusion/id6762097327)

All apps by Sultan Haider: https://appshunter.io/developer/1669774421

## Related topics

[lmstudio](https://appshunter.io/ios/topics/lmstudio) · [llm studio](https://appshunter.io/ios/topics/llm-studio)

---

*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 2026-11-14.*
