LLM Hub - Local AI Assistant

timmy boy

About this app

🤖 LLM Hub - Your Private AI Assistant

Advanced AI runs completely on your phone - no internet required, no data shared, complete privacy guaranteed. State-of-the-art Large Language Models in your pocket!

✨ FIVE POWERFUL AI TOOLS

📝 SMART CHAT
Multi-turn conversations with context awareness, RAG memory, optional web search, text-to-speech output with auto-readout, and support for text, images, and audio input.

✍️ WRITING AID
Summarize documents, expand ideas, rewrite content, improve grammar, and generate code from natural language descriptions.

🌍 TRANSLATOR (50+ Languages)
Translate text, images (OCR), and audio in real-time. Works completely offline with bidirectional support.

🎙️ TRANSCRIBER
Convert audio to text with high accuracy. Supports WAV. All processing on-device.

🛡️ SCAM DETECTOR
Analyze suspicious messages and images for phishing attempts. Get clear risk assessments and detailed explanations.

🚀 CUTTING-EDGE AI MODELS

• Gemma-3 1B (Google) - Fast and efficient
• Gemma-3n E2B/E4B (Google) - Multimodal: text, vision, audio
• Llama-3.2 1B/3B (Meta) - Powerful open-source
• Phi-4 Mini (Microsoft) - Optimized for mobile

All models run 100% on-device using MediaPipe and LiteRT technology.

🔐 PRIVACY & SECURITY

• Zero data collection - conversations stay on your device
• No internet required for AI inference
• No accounts, no tracking, no cloud uploads
• Open-source and transparent
• Complete offline functionality

⚡ ADVANCED FEATURES

• Text-to-Speech with auto-readout for hands-free listening
• GPU acceleration for fast performance
• Multimodal: text, images, and audio
• RAG with global memory for enhanced responses
• Import custom .task or .litertlm models
• Direct downloads from HuggingFace
• Beautiful Material Design UI
• 13 language interfaces

📱 REQUIREMENTS

Minimum: Android 8.0+, 2GB RAM, 1-5GB storage
Recommended: 6GB+ RAM, 8GB+ for GPU acceleration

💡 HOW IT WORKS

1. Download AI models in-app (one-time)
2. Choose your tool: Chat, Writing Aid, Translator, Transcriber, or Scam Detector
3. Use AI completely offline with full privacy
4. Optional: Enable web search, upload images/audio, or use text-to-speech

🌟 PERFECT FOR

• Privacy-conscious users valuing data security
• Professionals needing offline AI assistance
• Users wanting hands-free voice responses
• Students working on writing and research
• Travelers requiring offline translation
• Anyone protecting against scams
• Developers experimenting with on-device AI
• Content creators and writers

📖 OPEN SOURCE (MIT License)
github.com/timmyy123/LLM-Hub

🏆 POWERED BY
Google MediaPipe & LiteRT, Gemma, Llama, Phi models, HuggingFace

Experience the future of private, on-device AI assistance!

Ratings and reviews

Hi! I really appreciate your app—it’s been very helpful for offline document analysis. I have two feature requests: 1. Please consider increasing the 15,000-character limit so longer documents can be fully processed. 2. It would be great if users could load GGUF models directly from local device storage. Thanks for your great work!

Gemma 3n crashes. Can you add voice input via the microphone into it and having it talk back to you in tts? that would be cool.

can we get audio output we already have lots of text to text I want audio to audio that would be very nice and very unique please work on that guys hope seeing an update one day but so far this is good

What's new

Fixed an issue where the response was getting stuck with no content.