LLM Hub is an open-source Android app for on-device LLM chat and image generation. It's optimized for mobile usage (CPU/GPU/NPU acceleration) and supports multiple model formats so you can run powerful models locally and privately.
🍎 iOS version is coming! I'm actively working on it and would love to bring LLM Hub to iPhone and iPad. The only thing standing in the way is hardware — I need to save up ~$1,000 for a Mac and an Apple Developer account.
If you've enjoyed the app and want to help make iOS happen, even a small amount goes a long way 💙
Early sponsor perk: The iOS app will be a paid App Store release, but anyone who sponsors before launch gets a free redemption code on me. Just include your GitHub username or email in your sponsor note and I'll make sure you're taken care of when it ships!
| Tool | Description |
|---|---|
| 💬 Chat | Multi-turn conversations with RAG memory, web search, TTS auto-readout, and multimodal input |
| 🤖 creAItor | [NEW] Design custom AI personas with specialized system prompts (PCTF) in seconds |
| 💻 Vibe Coder | [NEW] Explain your app idea and watch it be built in real-time with live HTML/JS preview |
| ✍️ Writing Aid | Summarize, expand, rewrite, improve grammar, or generate code from descriptions |
| 🎨 Image Generator | Create images from text prompts using Stable Diffusion 1.5 with swipeable gallery |
| 🌍 Translator | Translate text, images (OCR), and audio across 50+ languages - offline |
| 🎙️ Transcriber | Convert speech to text with on-device processing |
| 🛡️ Scam Detector | Analyze messages and images for phishing with risk assessment |
- Vibes: A full on-device coding environment. The LLM writes HTML/JS/CSS based on your requirements, and you can preview/run the app instantly in a secure sandbox.
- creAItor: Powerful persona generation to create anything from characters with fun personalities to system architects. Just describe a creAItor ("respond like a pirate" or "respond with a markdown spec for a code agent to generate a full-stack system"), and the on-device LLM generates a complex system prompt (PCTF format) that you can use in chat.
Activate this in Settings under Kid Mode. Set a PIN, and the mode will remain in effect until you unlock it with the same PIN.
- Safe Exploration: Families can introduce children to private local AI with confidence.
- Model-Level Guardrails: Automatically activates strict safety protocols at the model inference layer across all tools (Chat, Writing Aid, Image Gen, etc.).
- Peace of Mind: Ensures all generated content is age-appropriate without compromising the privacy benefits of on-device processing.
- 100% on-device processing - no internet required for inference
- Zero data collection - conversations never leave your device
- No accounts, no tracking - completely private
- Open-source - fully transparent
- GPU/NPU acceleration for fast performance
- Text-to-Speech with auto-readout
- RAG with global memory for enhanced responses
- Import custom models (.task, .litertlm, qnn,.mnn, .gguf)
- Direct downloads from HuggingFace
- 16 language interfaces
Quick Start
- Download from Google Play or build from source
- Open Settings → Download Models → Download or Import a model
- Select a model and start chatting or generating images
Supported Model Families (summary)
- Gemma (LiteRT Task)
- Llama (Task + GGUF variants)
- Phi (LiteRT LM)
- LiquidAI LFM (LFM 2.5 1.2B + LFM VL 1.6B vision-enabled)
- Ministral / Mistral family (GGUF / ONNX)
- IBM Granite (GGUF)
Model Formats
- Task / LiteRT (.task): MediaPipe/LiteRT optimized models (GPU/NPU capable)
- LiteRT LM (.litertlm): LiteRT language models
- GGUF (.gguf): Quantized models — CPU inference powered by Nexa SDK; some vision-capable GGUF models require an additional
mmprojvision project file - ONNX (.onnx): Cross-platform model runtime
GGUF Compatibility Notes
- Not all Android devices can load GGUF models in this app.
- GGUF loading/runtime depends on Nexa SDK native libraries and device/ABI support; on unsupported devices, GGUF model loading can fail even if the model file is valid.
- In this app, the GGUF NPU option is intentionally shown only for Snapdragon 8 Gen 4-class devices.
Importing models
- Settings → Download Models → Import Model → choose
.task,.litertlm,.qnn,.gguf, or.mnn - The full model list and download links live in
app/src/.../data/ModelData.kt(do not exhaustively list variants in the README)
Technology
- Kotlin + Jetpack Compose (Material 3)
- LLM Runtime: MediaPipe, LiteRT, Nexa SDK
- Image Gen: MNN / Qualcomm QNN
- Quantization: INT4/INT8
Acknowledgments
- Nexa SDK — GGUF model inference support (credit shown in-app About) ⚡
- Google, Meta, Microsoft, IBM, LiquidAI, Mistral, HuggingFace — model and tooling contributions
Development Setup
git clone https://github.com/timmyy123/LLM-Hub.git
cd LLM-Hub/android
./gradlew assembleDebug
./gradlew installDebugTo use private or gated models, add your HuggingFace token to android/local.properties (do NOT commit this file):
HF_TOKEN=hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxSave and sync Gradle in Android Studio; the app will read BuildConfig.HF_TOKEN at build time.
To skip ads and unlock all premium features locally without a real IAP purchase, add this to android/local.properties:
DEBUG_PREMIUM=trueSet it back to false before making a production build.
Some models on HuggingFace (especially from Google and Meta) require explicit license acceptance before downloading. When building the app locally:
- Ensure you have a valid HuggingFace read token in
local.properties(see above) - For each model you want to download:
- Visit the model's HuggingFace page (e.g., https://huggingface.co/google/gemma-3n-E2B-it-litert-lm)
- Click the "Access repository" or license acceptance button
- Grant consent to the model's license terms
- Try downloading the model in the app again
Note: This is only required for local development builds. The Play Store version uses different authentication and does not require manual license acceptance for each model.
- macOS with Xcode installed (use a version that matches your iOS device version)
- An Apple ID signed into Xcode (free Personal Team works for local device testing)
- iPhone with Developer Mode enabled if you run on real hardware
- Clone the repo and open the iOS project:
git clone https://github.com/timmyy123/LLM-Hub.git
cd LLM-Hub
open ios/LLMHub/LLMHub.xcodeproj- In Xcode, select target LLMHub → Signing & Capabilities:
- Set your Team
- Set a unique Bundle Identifier (for example:
com.yourname.llmhub) - Keep Automatically manage signing enabled
- Select your iPhone as the run destination and press Run.
If your phone is on a newer iOS build and requires Xcode beta support, switch CLI tools:
sudo xcode-select -s /Applications/Xcode-beta.app/Contents/Developer
xcodebuild -version- If signing fails, re-check Team + Bundle Identifier in target settings.
- If build cache acts stale, clean DerivedData:
rm -rf ~/Library/Developer/Xcode/DerivedData/LLMHub-*- Build logs: Report Navigator (
Cmd+9) - Runtime logs: Debug Console (
Cmd+Shift+Y)
Contributing
- Fork → branch → PR. See CONTRIBUTING.md (or open an issue/discussion if unsure).
License
- Source code is licensed under the PolyForm Noncommercial License 1.0.0.
- You are free to use, study, and build on this project for non-commercial purposes.
- Commercial use — including distributing the app, charging for it, or monetizing it with ads or IAP — is not permitted without explicit written permission from the author.
- Contact timmyboy0623@gmail.com for commercial licensing enquiries.
Support
- Email: timmyboy0623@gmail.com
- Issues & Discussions: GitHub
Notes
- This README is intentionally concise — consult
ModelData.ktfor exact model variants, sizes, and format details.