Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Run local LLMs like Gemma, Qwen, and LLaMA on Android for offline, private, real-time chat and question answering with LiteRT and ONNX Runtime.
| Date | Stars |
|---|---|
| 2026-07-31 | 372 |
| 2026-08-04 | 374 |
| 2026-08-06 | 374 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# 🤖 Pocket LLM for Android (Offline, Private & Fast)
An Android application that brings local LLM chat, voice input, image input, OCR, and camera-based prompting to your phone.
Pocket LLM runs fully on device after model download. It supports ONNX-based Qwen models, LiteRT-based Qwen 3 and Gemma 4 models, streaming responses, persistent local chat history, markdown-rendered replies, downloadable models, in-app model switching, editable model instructions, and multiple image input workflows.
The app ships as a small base APK. Users download only the models they want, switch between them inside the app, and delete unused models later to save device storage.
---
[](https://github.com/dineshsoudagar/local-llms-on-android/releases)
---
## 🆕 New in v1.5.0
Pocket LLM now supports richer local input workflows beyond text chat.
- 🎙️ Added voice input for faster prompting
- 🖼️ Added image input with OCR and Gemma direct image input
- 📷 Added camera capture with retake, crop, and photo review
- 🗂️ Added a side panel for quick access to previous chats
- 🗑️ Added easier chat deletion from the history panel
- 💾 Added downloaded model deletion to free device storage
- ⚙️ Added editable model instructions with presets and custom prompts
- 🎨 Added dark mode, light mode, accent colors, and chat font-size control
- 📋 Added copy button for assistant responses
#### ➡️ [See all releases](https://github.com/dineshsoudagar/local-llms-on-android/releases)
---
### 🔗 Also Check Out
**[local-document-intelligence](https://github.com/dineshsoudagar/local-document-intelligence)**
A privacy-first offline document intelligence system with persistent local RAG, hybrid retrieval, and source-grounded answers.
---
## ✨ Features
- 📱 Fully on-device LLM chat for private offline use
- 🎙️ Voice input for faster prompting
- 🖼️ Image input with OCR and Gemma native image support
- 📷 Camera capture with retake, crop, and photo review
- 💬 Persistent multi-turn chat with local history
- 📦 Download, switch, and delete models inside the app
- 🧠 Supports Qwen2.5, Qwen3, Qwen3 LiteRT, and Gemma 4 LiteRT models
- ⚡ ONNX and LiteRT backend support
- 🎛️ Editable model instructions with presets and custom prompts
- 🎨 Light mode, dark mode, accent colors, and adjustable chat font size
- 🔐 Offline after model download, with no telemetry
---
## 📸 Inference Preview
<table align="center">
<tr>
<td align="center">
<img src="data/Chat.gif" alt="Model Output 1" width="260"/><br/>
<sub><b>Chat Inference</b></sub>
</td>
<td align="center">
<img src="data/Image support.gif" alt="Model Output 2" width="260"/><br/>
<sub><b>Image Support</b></sub>
</td>
<td align="center">
<img src="data/New ui.gif" alt="Chat UI Preview" width="260"/><br/>
<sub><b>New UI</b></sub>
</td>
</tr>
</table>
<p align="center">
<em>Figure: Pocket LLM showing offline chat, image input, and the updated Android UI.</em>
</p>
---
## 📦 Download APK - v1.5.0
The app ships as a **single smaller base APK**.
#### ➡️ [Download APK](https://github.com/dineshsoudagar/local-llms-on-android/releases/download/v1.5.0/pocket_llm_v1.5.0.apk)
Models are **not bundled inside the APK**. After installation, choose and download the models you want directly on device.
You can download **multiple models**, switch between them inside the app, and delete unused downloaded models later to free storage.
### Available chat models
- **Gemma 4 E4B LiteRT** - Best for **flagship mobiles**
- **Gemma 4 E2B LiteRT** - Best for **decent to mid-range mobiles**
- **Qwen3 0.6B LiteRT** - Best for **low-end mobiles**
- **Qwen3 0.6B Q4F16 ONNX** - Good for **low to mid-range mobiles**
- **Qwen2.5 0.5B ONNX** - Best for **mid to high-end mobiles**, **full precision**
### Image input support
- **Excerpt of 6,729 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:f956a2106aa14233, topic:qwen
matched fp:f956a2106aa14233, topic:chatbot