What is Private LLM?
Private LLM is an offline AI chat application that runs open-source language models locally on iPhone, iPad, and Mac. It requires no internet connection after the initial model download and stores all conversations on-device without accounts or tracking. A single purchase unlocks the app across Apple platforms and Family Sharing.
What are the features of Private LLM?
- Local model executionRuns over 140 open-source models including DeepSeek R1 Distill, Llama 3.3 70B, Qwen3 4B, Phi 4, and Gemma 3 directly on Apple hardware.
- Optimized quantizationShips OmniQuant and GPTQ builds tuned per model so 3-bit output matches the 4-bit quality of other apps.
- Shortcuts and Siri integrationConnects to Apple Shortcuts and Siri to build workflows that pipe responses into over 70 apps supporting x-callback-url.
- macOS text actionsRewrites, summarizes, or corrects selected text in any macOS app via a right-click menu in English and major Western European languages.
- Model browserFilters available models by device, RAM, and use case such as coding, reasoning, multilingual, or biomedical tasks.
- Beta capabilities (Private LLM 2)Adds vision models, document chat, web search, and tool support in the current beta release.
What are the use cases of Private LLM?
- Offline AI workflowsRunning local models through Apple Shortcuts to summarize text or generate writing without sending data to cloud servers.
- On-device text editingSelecting text in any macOS application to rewrite or correct it using a local model without an internet connection.
Private LLM Pricing Information:
- One-time purchaseSingle payment with no subscription; unlocks the app on iPhone, iPad, and Mac for the buyer and up to six people via Family Sharing.









