Private LLM
A local LLM app for iPhone, iPad, and Mac that works offline after model download, keeps chats on-device, and connects to Siri and Apple Shortcuts.
Private LLM runs AI chat entirely on your iPhone, iPad, or Mac. It's an app for people who want to use language models without sending their conversations to a cloud service. After the first model download, it works offline and requires no account. Conversations stay on-device, with no tracking or logs.
Its model selection includes DeepSeek R1 Distill, Llama 3.3, Qwen3, Phi 4, and Google Gemma 3. A model picker recommends choices for your device, and the catalog lets you filter by available RAM and intended use. The app offers uncensored chat, so model choice also matters when comparing how it responds to different prompts.
Siri and Apple Shortcuts support extends the app beyond a chat window. You can use local AI to summarize text, generate writing, and pass responses to apps that support x-callback-url, without writing code. On macOS, built-in writing tools can rewrite, summarize, or correct selected text in other apps. They support English and major Western European languages.
Private LLM uses OmniQuant and GPTQ to reduce model memory needs while limiting the loss of output quality. It pairs those methods with Metal kernels tuned for individual models on Apple hardware. That approach is a technical distinction for readers comparing apps that run the same models locally.
