UnPlugged LM

Your AI. Your data. Your device. UnPlugged LM is a fully private, offline AI assistant that runs entirely on your iPhone or iPad — no internet connection required, no data ever leaves your device, no subscriptions. What you get: CHAT Talk to a local large language model (LLM) powered by llama.cpp. Responses stream token by token directly from your device's CPU. Full chat history saved locally in SQLite. DOCUMENTS & RAG Import PDFs and Word documents. UnPlugged LM reads, chunks, and embeds them on-device so you can ask questions grounded in your own files — legal contracts, medical notes, research papers, anything. PROJECTS Organise your documents and conversations into separate workspaces. Each project keeps its own RAG context so topics never bleed into each other. MODELS Download and manage open-weight GGUF models — Phi-3 Mini, Llama 3, Gemma 2, Mistral, and more. Models are stored in your app's private Documents folder. Switch between them any time. Pro features (one-time purchase, $9.99): LOCAL AI SERVER Turn your iPhone into a local AI server. UnPlugged LM provides a private local REST API over Wi-Fi so trusted apps and devices on the same network can use your phone's AI — no cloud, no cost. Includes a built-in browser chat UI protected by an optional access code. Your browser sessions are saved to your phone's chat history automatically. Voice Input & Output, Device Actions, Scheduled Tasks, Morning Briefing, Smart Notifications, and Unlimited Projects — coming as Pro rolls out. Privacy promise: • Zero telemetry — no analytics, no crash reporters, no trackers • No account required — ever • All inference runs on your CPU via llama.cpp • Documents stay in your app's sandboxed storage • The local server never reaches the internet — Wi-Fi only My Device. My Rule. Developed by SmartDataIQ — unpluggedlm.com