Skip to content

Reins: for Ollama & LM Studio

Take the Reins of your AI. R

About this app

<p>Take the Reins of your AI.</p>
<p>Reins connects to your Ollama, LM Studio or any OpenAI-compatible server and runs local AI models directly on-device. It brings powerful AI models like Gemma, Qwen, Llama and more to your iPhone and iPad — with tools, web search, and full control over every conversation. No login. No data collection.</p>
<p>PLUG-n-PLAY<br />
Either connect to your Ollama, LM Studio or OpenAI-compatible server, or run models on-device. Reins just works, keeps everything private, every chat stays yours.</p>
<p>TOOLS & WEB SEARCH<br />
Go beyond chat. Reins gives models the ability to search the web, fetch pages, calculate and reason across multiple steps — no API key required for web search.</p>
<p>FULL MODEL CONTROL<br />
Download, switch and manage your models directly from the app. Connect multiple servers, configure API keys and custom headers and switch between them instantly. Access Ollama Cloud when you need it.</p>
<p>POWERFUL CHAT<br />
Attach images, PDFs, CSVs and text files to any conversation. Enable thinking mode for deeper reasoning when you need it. Branch chats to explore different paths without losing your original thread. Never lose a cut-off response, pick up exactly where it stopped. Export or back up your conversations anytime.</p>
<p>FINE-GRAINED CONTROL<br />
Set a different system prompt for every conversation. Dial in temperature, context size, max tokens and more for precise control over model behavior.</p>
<p>ON DEVICE MODELS<br />
Run AI models directly on your iPhone and iPad without any setup. It's powered by MLX to achieve the best performance on Apple Silicon. You can download any MLX model even if it's not listed in the library. Reins also works with Apple Intelligence's on-device Foundation Models.</p>
<p>BACKGROUND PROCESSING<br />
No need to wait around for complex reasoning, long responses or model downloads. Switch apps or lock your screen and Reins keeps generating in the background. Come back and it'll be waiting for you. (Requires iOS or iPadOS 26.0+)</p>
<p>Reins works with your Ollama, LM Studio or OpenAI-compatible server, or runs AI models on-device with no server required. Self-hosted or Ollama Cloud both work too.</p>
<p>Privacy Policy: https://getreins.app/privacy<br />
Terms of Use: https://getreins.app/terms</p>

What stands out

Connects to Ollama, LM Studio, or OpenAI-compatible servers, or runs models locally via MLX.
Supports on-device inference on Apple Silicon with no internet connection required.
Includes built-in web search, tool use, and multi-step reasoning capabilities.
Allows fine-grained control over system prompts, temperature, and context window.

Version updates

Version 2.3.2

On-Device models are here. Run AI models directly on your iPhone and iPad. Share them across your local network if you want to. • On-Device models: Powered by MLX for the best performance on Apple Silicon, with support for all of Reins' features. • Local network sharing: Expose models on your iPhone or iPad over an Ollama- or OpenAI-compatible endpoint for other devices to use. • Download any MLX model: Search for a specific model and download it even if it's not listed in the library. • Tool calling is now available for MiniCPM5 on-device models. • The LFM 2.5 2.6B on-device model now works. It previously failed to run. • Bug fixes and improvements.

9 月 29, 2026 · Apple App Store · iOS · View source

Version 2.3.1

On-Device models are here. Run AI models directly on your iPhone and iPad. Share them across your local network if you want to. • On-Device models: Powered by MLX for the best performance on Apple Silicon, with support for all of Reins' features. • Local network sharing: Expose models on your iPhone or iPad over an Ollama- or OpenAI-compatible endpoint for other devices to use. • Download any MLX model: Search for a specific model and download it even if it's not listed in the library. • Fixed an issue where some on-device models' thinking process could appear in the message content instead of the thinking block. • Bug fixes and improvements.

9 月 20, 2026 · Apple App Store · iOS · View source

Version 2.3.0

On-Device models are here. Run AI models directly on your iPhone and iPad. Share them across your local network if you want to. • On-Device models: Powered by MLX for the best performance on Apple Silicon, with support for all of Reins' features. • Local network sharing: Expose models on your iPhone or iPad over an Ollama- or OpenAI-compatible endpoint for other devices to use. • Download any MLX model: Search for a specific model and download it even if it's not listed in the library. • Bug fixes and improvements.

9 月 17, 2026 · Apple App Store · iOS · View source

AppRank score

The average of the verified ratings available across this app’s platforms.

★ 4.6307 ratings
Cross-platform average

Reviews

kirby1976 ★ 5.0

Indispensable, Great Support

Very useful and configurable. I use this with a model on my network. I had excellent support and qui…
From iOS · 10 月 10, 2026 · View source
h4l9k ★ 5.0

Looks awesome

I liked it, it works well and the price is reasonable. If there was a Windows app I would consider i…
From iOS · 10 月 10, 2026 · View source
Covetspartan ★ 1.0

Useless

This app used to be fun, but now they’ve locked out basic functionality behind a subscription, even …
From iOS · 10 月 10, 2026 · View source
Jabmist ★ 2.0

Only for pro

Description says it connects to what ever servers you want and it allows to use.. some how I doesn’t…
From iOS · 10 月 10, 2026 · View source
Olivine Cat ★ 2.0

Used to be decent, now charges a subscription (or $100) to use basic model features on local hosts

Thinking and tool use are basic features provided by the already running ollama server. I get gating…
From iOS · 10 月 10, 2026 · View source
Bkmmkb ★ 1.0

Subscription walled

When I first got the app it seemed to have decent functionality but now every basic feature is behin…
From iOS · 10 月 10, 2026 · View source
Netapp76 ★ 1.0

Subscription not worth it

Tool calls do not work
From iOS · 10 月 10, 2026 · View source
Tee veer ★ 1.0

Loved it as FOSS, useless now

Paywalling everything after stopping the code releases is the fastest way to lose goodwill. I would …
From iOS · 10 月 10, 2026 · View source
Harry Azzcrak ★ 5.0

Local LLM AI

THIS THING WORKS
From iOS · 10 月 10, 2026 · View source
Ben Hetrick ★ 5.0

Simple, Direct, Excellent

I really appreciate having a simple app to just plug into a local model im running and prompt it imm…
From iOS · 10 月 10, 2026 · View source

Sign in to rate and review

Create a free account or sign in to leave a rating and review. Your name and email stay linked to your account.

You may also like

Recommendations use shared purpose, platform availability and rating confidence.

Popular comparisons

Compare features, pricing & platforms side by side.