Private LLM

Private LLM runs AI chat on iPhone, iPad and Mac for people who want to use language models without sending conversations to a cloud service. It works offline after the first model download and doesn't require an account.

• Local model choice: Chat with models including DeepSeek R1 Distill, Llama 3.3, Qwen3, Phi 4 and Google Gemma 3, with uncensored chat available.
• Device-aware selection: The model catalog filters choices by device, RAM and use case, and a picker recommends models for your hardware.
• Siri and Shortcuts: Use local AI in Apple Shortcuts to summarize text, generate writing and pass responses to apps that support x-callback-url, without writing code.
• Writing across Mac apps: Built-in macOS writing tools rewrite, summarize or correct selected text entirely on-device, with support for English and major Western European languages.

Private LLM is a paid app for Apple's platforms. Conversations stay on the device, and the app states that it uses no tracking or logs. Its model builds use OmniQuant and GPTQ quantization to reduce memory needs, paired with model-specific Metal kernels for Apple hardware.