# Private LLM

> Private LLM is a one-time-purchase local AI chat app for iPhone, iPad, and Mac. It runs open-source language models (DeepSeek R1, Llama 3.3 70B, Qwen3, Phi 4, Gemma 3) entirely on-device with OmniQuant quantization — no internet, no account, no subscription, no data collection.

Private LLM is built by Numen Technologies Limited, an independent EU-based company (Ireland and Netherlands). The inference engine is proprietary; the models it runs are open-source. Apple Silicon Macs with 48GB+ RAM can run the Llama 3.3 70B model locally. Smaller models (1B–8B) run on iPhones and iPads with 4GB+ RAM. The app is distributed exclusively through the Apple App Store.

## Key pages

- [Home](https://privatellm.app/en): Product overview, features, supported models
- [FAQ](https://privatellm.app/en/faq): Technical answers, refund policy, hardware requirements, Family Sharing, comparison with Ollama and LM Studio
- [Reviews](https://privatellm.app/en/reviews): Localized App Store review archive for iOS and macOS
- [Community Shortcuts](https://privatellm.app/en/community-shortcuts): User-built Siri and Apple Shortcuts workflows

## Comparisons

- [Private LLM vs Ollama](https://privatellm.app/compare/ollama-vs-private-llm): Quantization quality and iOS support differences
- [Private LLM vs LM Studio](https://privatellm.app/compare/lm-studio-vs-private-llm): Native Swift app vs Electron desktop app
- [Private LLM vs LLM Farm](https://privatellm.app/compare/llm-farm-vs-private-llm): Mac + iOS coverage and UX comparison
- [Private LLM vs PocketPal AI](https://privatellm.app/compare/pocketpal-ai-vs-private-llm): Feature and model support comparison
- [Private LLM vs Apollo AI](https://privatellm.app/compare/apollo-ai-vs-private-llm): Feature and model support comparison

## Guides

- [Run Local GPT on iOS: Complete Guide](https://privatellm.app/blog/run-local-gpt-on-ios-complete-guide): Full setup, sampling settings, system prompts, model-to-device sizing, and integrations
- [Choosing the Right AI Model for iPhone and iPad](https://privatellm.app/blog/run-local-gpt-on-ios-complete-guide#choosing-the-right-ai-model-for-iphone-and-ipad): Hardware-to-model sizing guide (section)
- [Choosing the Right AI Model for Mac](https://privatellm.app/blog/run-local-gpt-on-ios-complete-guide#choosing-the-right-ai-model-for-mac): Apple Silicon model recommendations (section)
- [Understanding System Prompts](https://privatellm.app/blog/run-local-gpt-on-ios-complete-guide#understanding-system-prompts): System prompt authoring guide (section)
- [Understanding Sampling Settings](https://privatellm.app/blog/run-local-gpt-on-ios-complete-guide#understanding-sampling-settings): Temperature and Top-P tuning (section)
- [Best Uncensored LLMs to Run with Private LLM](https://privatellm.app/blog/best-uncensored-ai-chat-run-locally-iphone-ipad-mac-2026): Uncensored model roundup

## Policies

- [Privacy Policy](https://privatellm.app/en/privacy-policy): No data collection, fully on-device inference
- [Press Kit](https://privatellm.app/press-kit): Brand assets and media resources