#1515th of 16 in Desktop AI apps
pocketpal-ai
Phone app that runs GGUF language models offline on iOS and Android
- Stars
- 8.7k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- TypeScript
6,185 on 1 Apr 20268,746 on 21 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
PocketPal AI is a React Native app for iOS and Android that runs quantized GGUF language models on the phone through llama.rn and llama.cpp. It adds on-device text-to-speech via ONNX Runtime (Kokoro and others), configurable Pals with their own system prompts, and a tool-use loop with calculator, date/time and HTML-render tools. Models are downloaded from Hugging Face, and a built-in benchmark reports tokens/sec and memory.
Who it is for: Phone users wanting private offline LLM chat, and React Native developers
Strengths
- Chat, TTS and tool calls run on-device with no account or internet after model download
- Searches and downloads GGUF models from Hugging Face, including gated ones with a token
- CPU, Metal, OpenCL (Adreno) and Qualcomm Hexagon NPU paths with graceful fallback
- Built-in benchmark for tokens/sec and memory, with optional public leaderboard
Weaknesses
- Only three built-in tools: calculate, datetime and render_html
- Mobile only; no desktop or server build is described
- Model size is limited by phone RAM; the README gives no minimum
- Some Pals on PalsHub are premium via in-app purchase
What it needs
- GPU optional
- Needs llama.rn, llama.cpp, ONNX Runtime, WatermelonDB
- Models: GGUF, ONNX (TTS)
Also in Desktop AI apps
See all 16| Rank | Project | Score |
|---|---|---|
| 1 | prompt-optimizerPrompt rewriting and testing tool for web, desktop, Chrome and MCP | 81 out of 100 |
| 2 | cherry-studioCross-platform desktop chat client for many cloud and local LLM providers | 80 out of 100 |
| 3 | deep-live-camReal-time webcam face swap from a single source image | 76 out of 100 |
| #4 | screenpipeRecords screen and audio locally, makes it searchable for you and your agents | 75 out of 100 |
| #5 | dsh-desktopNative Windows and macOS desktop client for DeepSeek Harness | 74 out of 100 |