Private LLM - Local AI Chat

Private LLM is a privacy-first, on-device AI assistant for iOS that runs offline and does not require a subscription. It employs a fast, optimized mlc-llm inference engine and OmniQuant quantization to deliver responsive conversations entirely on your device, supporting a wide range of open-source models from Llama, Gemma, Qwen, Mistral, and more.

Features include Siri and Shortcuts integration, customizable system prompts, Family Sharing, and offline model downloads. The app emphasizes privacy and security, making it ideal for creative writing, coding help, and everyday queries without data ever leaving your device.