off-grid-ai/mobile

The Swiss Army Knife of Offline AI. Chat, Speak, and Generate Images - Privacy First, Zero Internet. Download an LLM and use it on your mobile device. No data ever leaves your phone. Supports text-to-text, vision, text-to-image

What it solves

Off Grid AI provides a complete, private AI suite that runs entirely on-device, eliminating the need for cloud connectivity and preventing data from leaving the user's phone or Mac. It solves the problem of privacy-conscious users needing access to diverse AI capabilities (text, image, vision, and voice) without relying on external servers.

How it works

The application leverages native hardware acceleration (NPU on Snapdragon, Core ML on iOS) and optimized libraries like llama.cpp and whisper.cpp to run models locally. It supports GGUF models for text generation, Stable Diffusion for images, and Whisper for speech-to-text. It also includes a local RAG system using a bundled MiniLM model and SQLite for document analysis and project knowledge bases.

Who it’s for

Privacy-focused individuals, developers, and users on Android, iOS, and macOS who want a versatile, offline AI assistant that can handle multimodal tasks without data harvesting.

Highlights

  • Multimodal Capabilities: Supports text generation (Llama 3.2, Phi-4, etc.), image generation (Stable Diffusion), vision AI (SmolVLM, Qwen3-VL), and voice transcription (Whisper).
  • Local RAG: On-device embedding and retrieval of PDFs and text documents for project-specific knowledge bases.
  • Tool Calling: Built-in tools for web search, calculators, and knowledge base search with runaway prevention.
  • Flexible Model Support: Ability to bring your own .gguf files or connect to OpenAI-compatible local servers like Ollama or LM Studio.
  • Privacy First: Zero data leaves the device; all processing, including voice and image generation, happens in local RAM/NPU.