LLM Hub - Local AI Assistant

timmy boy

About this app

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!

✨ SIX 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.

🎨 IMAGE GENERATOR
Create stunning images from text prompts using Stable Diffusion 1.5. Generate multiple variations with swipe-through gallery. All processing happens on-device.

🌍 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
• Stable Diffusion 1.5 - On-device image generation

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

🔐 PRIVACY & SECURITY

• Zero data collection - everything stays on your device
• No internet required for AI inference
• No accounts, no tracking, no cloud uploads
• Open-source and transparent

⚡ ADVANCED FEATURES

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

📱 REQUIREMENTS

Minimum: Android 8.0+, 2GB RAM, 1-5GB storage
Recommended: 6GB+ RAM for best performance

💡 HOW IT WORKS

1. Download AI models in-app (one-time)
2. Choose your tool: Chat, Writing Aid, Image Generator, 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
• Artists and creators generating AI images
• Users wanting hands-free voice responses
• Students working on writing and research
• Travelers requiring offline translation
• Anyone protecting against scams

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

🏆 POWERED BY
Google MediaPipe & LiteRT, MNN, Stable Diffusion, Gemma, Llama, Phi, HuggingFace

Experience the future of private, on-device AI!

Ratings and reviews

This is a really slick app, simple smooth menu, no overly complicated options. No invasive unnecessary permissions, no ads and it just works. The only issue I ran into was while downloading the models it would pause downloading if I left the download screen, not a huge issue since you only download once. Would recommend to anyone.

Has potential. chatting is fast and smooth but image generation... slow (expected) but if you jump to another app while generating for an hour it'll reset everything when you return! please fix that.

So much wasted potential so far. No SD card. No background long tasks - the model stops when you switch chat. Voice input is limited to 30 seconds and doesn't allow real-time interaction. No auto model benchmarking (some produce garbled output). Very trivial tools are available. Web search blocks process, generally quite unresponsive, nothing works in parallel. Vision model means "can upload pdf". No history disable. Cumbersome RAG. No agentic progressive automation, just a trivial chat. GL tho!

What’s new

Optimized UI for tablets and foldables