# LLM runner (local 100%) — On-device AI chat, no network

> On-device AI chat, no network (iPhone/iPad app by Valerii Lubnin.)

- Source: https://appshunter.io/ios/app/llm-runner-local-100/id6801577666 (this page in markdown: same URL + `.md`)
- Developer: [Valerii Lubnin](https://appshunter.io/developer/6801577669)
- Category: Productivity, Education
- Price: Free
- Age rating: 9+
- Requires: iOS 18.0 · 19 MB
- Languages: American English, Russian
- Released: 2026-08-26
- Data updated: 2026-09-14
- User reviews in markdown: https://appshunter.io/ios/app/llm-runner-local-100/id6801577666/reviews.md

## What is LLM runner (local 100%)?

Run LLM on your iPhone, 100% local, no network
(Network needed once to download a model)

Models:

• Qwen2.5 0.5B Instruct — ~0.4 GB (4 GB RAM)
• Llama 3.2 1B Instruct — ~0.8 GB (4 GB RAM)
• Qwen2.5 1.5B Instruct — ~0.9 GB (4 GB RAM)
• Llama 3.2 3B Instruct — ~1.9 GB (6 GB RAM)
• Qwen3 4B Instruct 2507 — ~2.5 GB (6 GB RAM)
• Qwen2.5 7B Instruct — ~4.4 GB (8 GB RAM)

Requires iOS 18 or later.

Qwen models © Alibaba Cloud. Licensed under Apache License 2.0.

Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. Built with Llama.

On-device inference uses llama.cpp (MIT License).


## Version history (last 1 release)

### 0.1.537 — 2026-08-26

No release notes.

---

*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 2026-09-14.*