# Token : Local AI Studio — Run AI Models On Device

> Run AI Models On Device (iPhone/iPad app by MESUT CAN YAGCI.)

- Source: https://appshunter.io/ios/app/token-local-ai-studio/id6774354746 (this page in markdown: same URL + `.md`)
- Developer: [MESUT CAN YAGCI](https://appshunter.io/developer/1878989701)
- Category: Productivity
- Price: Free
- Age rating: 4+
- Requires: iOS 17.0 · 550 MB
- Languages: American English
- Released: 2026-05-30
- Data updated: 2026-08-03
- User reviews in markdown: https://appshunter.io/ios/app/token-local-ai-studio/id6774354746/reviews.md

## What is Token?

Token : LLM Manager brings powerful AI language and vision models directly to your iPhone — running entirely on-device, fully offline, with nothing ever leaving your device.

Download open models once, then chat, dictate, and analyze images anywhere — on a plane, underground, or off the grid. No subscription, no account, no cloud.

FEATURES
• On-device AI — language and vision models run locally using optimized GGUF and MLX engines
• Truly private — your conversations and data never leave your iPhone
• Works offline — once a model is downloaded, no internet connection is required
• Model library — browse and download open models, with hardware-matched suggestions for your device
• Chat — natural, fast conversations with your local assistant
• Voice — speak to your assistant and hear responses with on-device speech
• Vision — ask questions about photos and images using local vision-language models
• Multilingual — available in English, Turkish, Spanish, German, French and more

Token automatically suggests the best model for your device's hardware, so you get the fastest possible performance without guesswork.

Your AI. Your device. Your privacy.


## Version history (last 5 releases)

### 1.4 — 2026-07-08

• New app languages: Arabic, Greek, Romanian, Portuguese, and Russian
• Pick assistant reply language separately from the interface language
• Improved on-device tool calling and assistant chat experience
• Faster, more stable MLX and GGUF inference
• Refreshed settings and UI polish

### 1.3.3 — 2026-06-26

New: Conversation history drawer
Your saved chats now live in a slide-out side panel. Open it with the = button (top-left) or a swipe in from the left edge. Tap a chat to reopen it; swipe a row to delete or export. Tap the dimmed area to close.

New: On-device error analysis
Settings → Privacy → "Analyze errors with AI" feeds the app's local diagnostic report to your loaded model and explains likely causes of any crashes/errors — fully on-device, nothing uploaded.

Polish
Cleaner header, larger tap targets, and better text contrast on the light and dark themes.

Please test
*Open/close the history drawer with both the = button and the left-edge swipe; confirm rows are tappable and the panel is bright (not dimmed)
* Run "Analyze errors with AI" after a model is loaded
* General stability when switching models

### 1.3.2 — 2026-06-21

Fixes
*Qwen3-VL no longer errors when you attach a photo ("placeholder tokens
  does not match number of frames" is gone).
* Reasoning models (Qwen3, R1, QwQ) now finish their answer instead of
  getting cut off mid-thinking. If one ever does run out of room, you'll
  see a clear note instead of a blank reply.

New: Tool calling (optional)
*Turn on Settings → "Allow tools". The model can now call on-device
  tools to answer: calculator, memory search, date/time, unit/currency
  conversion, and OCR on an attached image. Web search is also available
  (this is the only tool that uses the internet).
* Works on tool-aware models (Qwen3, Llama 3.1) and GGUF models.

What to try
1. Attach a photo and ask Qwen3-VL to describe it — should work after a
   multi-turn chat.
2. Ask Qwen3-4B a hard question — confirm an answer follows the reasoning.
3. Enable "Allow tools", then ask: "what time is it", "convert 5 miles to
   km", or "search the web for something".

Note: with tools on, replies take a little longer (the model checks tools
first). Everything stays on-device except web search.

### 1.3.1 — 2026-06-17

Thanks for using TokenAI! Here is what we changed in this build:

 Check out our sister app!
We've added a spotlight card for "On Device : Local AI Studio"inside the settings page. Discover offline voice, chat, and vision options in seconds.
*Native App Store Ratings: We've updated our feedback prompt to use Apple's native StoreKit dialog, keeping rating requests non-disruptive and secure.
*Bug Fixes: Refined the settings interface to work flawlessly with our latest localized themes.

### 1.3.0 — 2026-06-15

This update makes every model you load run better — especially ones outside the built-in catalog:

• Fixed garbled characters in emoji, Turkish, Chinese and other non-English replies — characters split across tokens now always render correctly.
• Long chats now stop cleanly at the model's context limit instead of failing mid-reply with a generation error.
• More vision models (LLaVA, MiniCPM-V, Gemma-style and others) now use their native chat template for image and video questions — noticeably better answers.
• Downloads are verified the instant they finish: gated-repo error pages and corrupt model files are rejected with clear guidance instead of being saved as broken models.
• Memory safety: speculative decoding now checks free RAM before loading a draft model, and switching models mid-generation frees the old one immediately.
• Regenerating a response now keeps attached video clips.

## More apps by MESUT CAN YAGCI

- [Boo : IPTV Player](https://appshunter.io/ios/app/boo-iptv-player/id6759488654)
- [Till. --  Island & Activities](https://appshunter.io/ios/app/till-island-and-activities/id6759489910)
- [Hadis365](https://appshunter.io/ios/app/hadis365/id6760354368)
- [QuietNote](https://appshunter.io/ios/app/quietnote/id6760562505)
- [Vamp: Bureau à Distance](https://appshunter.io/ios/app/vamp-bureau-a-distance/id6762654508)
- [On Device : Local AI Studio](https://appshunter.io/ios/app/on-device-local-ai-studio/id6770114399)

All apps by MESUT CAN YAGCI: https://appshunter.io/developer/1878989701

## Related topics

[local ai studio](https://appshunter.io/ios/topics/local-ai-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 2026-08-03.*