Private LLM Local AI for Private, Uncensored Chat on iPhone, iPad, and Mac

No Cloud, No Tracking, No Logins.

No Internet? No Problem! Private LLM Works Anywhere, Anytime!

Private LLM is a local AI chatbot for iOS and macOS that works offline, keeping your information completely on-device, safe and private. It doesn't need the internet to work, so your data never leaves your device. It stays just with you. With no subscription fees, you pay once and use it on all your Apple devices. It's designed for everyone, with easy-to-use features for generating text, helping with language, and a whole lot more. Private LLM uses the latest AI models quantized with state of the art quantization techniques to provide a high-quality on-device AI experience without compromising your privacy. It's a smart, secure way to get creative and productive, anytime and anywhere.

A close-up view of an iPhone screen displaying the interface of the Private LLM app, where a text prompt is entered into a chat-like interface, highlighting the app's ability to run sophisticated language models locally on the device for enhanced privacy and offline functionality

Harness the Power of Open-Source AI with Private LLM

Private LLM brings the best of open-source AI directly to your iPhone, iPad, and Mac. With support for leading models like DeepSeek R1 Distill, Llama 3.3, Phi-4, Qwen 2.5, and Google Gemma 2, you can explore powerful AI capabilities, fully customized for your Apple devices and 100% private.

Find the Best Open-Source LLMs for Your Device

Screenshot of the Private LLM app on an iPhone, displaying a user-friendly interface with a list of downloadable Large Language Models (LLMs) available for offline use, showcasing a variety of model names and descriptions, emphasizing the app's capability for personalized AI experiences while highlighting its privacy and offline functionality.

Craft Your Own AI Solutions: No Code Needed with Siri and Apple Shortcuts

Discover the simplicity of bringing AI to your iOS or macOS devices without writing a single line of code. With Private LLM integrated into Siri and Shortcuts, users can effortlessly create powerful, AI-driven workflows that automate text parsing and generation tasks, provide instant information, and enhance creativity. This seamless interaction allows for a personalized experience that brings AI assistance anywhere in your operating system, making every action smarter and more intuitive. Additionally, Private LLM also supports the popular x-callback-url specification, which is supported by over 70 popular iOS and macOS applications. Private LLM can be used to seamlessly add on-device AI functionality to these apps.

Discover User-Created Apple Shortcuts Powered by Private LLM

An iPhone displaying the Private LLM app interface with an Apple Shortcut integration, showcasing a seamless user experience for personalizing AI interactions on iOS

Universal Access with No Subscriptions

Ditch the subscriptions for a smarter choice with Private LLM. A single purchase unlocks the app across all Apple platforms—iPhone, iPad, and Mac—while enabling Family Sharing for up to six relatives. This approach not only simplifies access but also amplifies the value of your investment, making digital privacy and intelligence universally available in your family.

Screenshot of the Private LLM interface on macOS, featuring a user typing a prompt into the application's text input field, ready to receive instant, offline responses from the local language model

AI Language Services Anywhere in macOS

Transform your writing across all macOS apps with AI-powered tools. From grammar correction to summarization and beyond, our solution supports multiple languages, including English and select Western European ones, for flawless text enhancement.

Screenshot showing the Private LLM integration within the macOS system-wide services menu.

Proudly Independent

We chose to bootstrap Private LLM because true innovation doesn't need venture capital. As an independent team of two developers, we're free to build the best local AI experience without compromising on our values. This independence lets us invest in advanced technologies like OmniQuant quantization while keeping your data completely private - choices we can make because we answer to users, not investors. With no pressure to monetize your data or rush features, we focus on what truly matters: building powerful local AI that respects your privacy and delivers superior performance.

Superior Model Performance With State-Of-The-Art Quantization

The core of Private LLM's superior model performance lies in its use of the state-of-the-art OmniQuant quantization algorithm. While quantizing LLMs for on-device inference, outlier values in LLM weights tend to have a marked adverse effect on text generation quality. Omniquant quantization handles outliers by employing an optimization based learnable weight clipping mechanism, which preserves the model's weight distribution with exceptional precision. RTN (Round to nearest) quantization used by popular open-source LLM inference frameworks and apps based on them, does not handle outlier values during quantization, which leads to inferior text generation quality. OmniQuant quantization paired with optimized model-specific Metal kernels, enables Private LLM to deliver text generation that is not only fast but also of the highest quality, significantly raising the bar for on-device LLMs.

Private LLM vs Ollama

See what our users say about us on the App Store

A distinct approach

by Original Nifty-Oct 12, 2024

This application is unique in creating the conditions for an interaction whose essence is of a noticeably superior quality., despite (and partly because of) the fact that the model is running completely locally! While at the time of writing the UI is in the early stages of development, it is still workable, easy and stable, allowing the interaction with the model to continue over an extended period. The developers take a distinct and very refreshing ethical position, and are most generous. I am very grateful to them.

Version 1.8.9|United Kingdom

Download the Best Open Source LLMs

iOS

DeepSeek R1 Distill Based Models

For iPhones/iPads with 8GB+ RAM

DeepSeek R1 Distill Llama 8B DeepSeek R1 Distill Qwen 7B DeepSeek R1 Distill Llama 8B Abliterated (Uncensored)

DeepSeek R1 Distill Based Models

For iPhones/iPads with 16GB+ RAM

DeepSeek R1 Distill Qwen 14B

Meta Llama 3.2 3B Based Models

For iPhones/iPads with 6GB+ RAM

Meta Llama 3.2 3B Instruct 🦙Llama 3.2 3B Instruct Abliterated 🦙 (Uncensored)Llama 3.2 3B Instruct Uncensored 🦙Hermes 3 Llama 3.2 3B FuseChat Llama 3.2 3B Instruct

Meta Llama 3.2 1B Based Models

For iPhones/iPads with 4GB+ RAM

Meta Llama 3.2 1B Instruct 🦙Llama 3.2 1B Instruct Abliterated 🦙 (Uncensored)FuseChat Llama 3.2 1B Instruct

Google Gemma 2 9B Based Models

For iPhones/iPads with 16GB+ RAM

Gemma-2 9B IT 💎Gemma-2 9B IT SPPO Iter3 Tiger Gemma 9B v3 🐅 (Uncensored)FuseChat Gemma 2 9B Instruct

Google Gemma 2 2B Based Models

For iPhones/iPads with 4GB+ RAM

Gemma-2 2B IT 💎SauerkrautLM Gemma-2 2B IT

Meta Llama 3.1 8B Based Models

For iPhones/iPads with 8GB+ RAM

Meta Llama 3.1 8B Instruct 🦙Meta Llama 3.1 8B Instruct Abliterated 🦙(Uncensored)Hermes 3 Llama 3.1 8B FuseChat Llama 3.1 8B Instruct Llama 3.1 8B Lexi Uncensored V2 (Therapy/Role-Play)

Meta Llama 3 8B Based Models

For iPhones/iPads with 6GB+ RAM

Meta Llama 3 8B Instruct 🦙Meta Llama 3 8B Instruct Abliterated v3 (Uncensored)NeuralDaredevil 8B Abliterated (Uncensored)Llama 3 8B Instruct MopeyMule Llama 3 WhiteRabbitNeo 8B v2.0 Hermes 2 Theta Llama 3 8B LLaMA3-iterative-DPO-final Hathor_Stable-v0.2-L3-8B Openchat 3.6 8B 20240522 Dolphin 2.9 Llama 3 8B (Uncensored) 🐬Llama 3 Smaug 8B Hermes 2 Pro Llama 3 8B ☤OpenBioLLM-8B 🧬L3 Umbral Mind RP v3.0 8B 🌓Llama 3 Instruct 8B SPPO Iter3

Qwen 2.5 Based Models

For iPhones/iPads with 4GB+ RAM

Qwen 2.5 0.5B Unquantized Qwen 2.5 Coder 0.5B Unquantized

Qwen 2.5 Based Models

For iPhones/iPads with 4GB+ RAM

Qwen 2.5 1.5B Qwen 2.5 3B Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 3B EVA-D Qwen2.5 1.5B v0.0 (Role-Play/Story Writing)

Qwen 2.5 Based Models

For iPhones/iPads with 8GB+ RAM

Qwen 2.5 7B FuseChat Qwen 2.5 7B Instruct EVA Qwen2.5 7B v0.1 (Role-Play/Story Writing)

Qwen 2.5 Based Models

For iPhones/iPads with 8GB+ RAM

Qwen 2.5 Coder 7B

Qwen 2.5 14B Based Models

For iPhones/iPads with 16GB+ RAM

Qwen 2.5 Coder 14B EVA Qwen2.5 14B v0.2 (Role-Play/Story Writing)

Phi-3 Mini 3.8B Based Models

For iPhones/iPads with 6GB+ RAM

Phi-3 Mini 4K Instruct Kappa-3 Phi Abliterated (Uncensored)

Google Gemma Based Models

For iPhones/iPads with 8GB+ RAM

Gemma 2B IT 💎Gemma 1.1 2B IT 💎

Mistral 7B Based Models

For iPhones/iPads with 6GB+ RAM

Mistral 7B Instruct v0.3 Mistral 7B Instruct v0.2 OpenHermes 2.5 Mistral 7B ☤Hermes 2 Pro Mistral 7B ☤RakutenAI 7B Chat 🇯🇵openchat-3.5-0106 7B 💬CodeNinja 1.0 OpenChat 7B 🥷Starling LM 7B Beta 🐤Dolphin 2.8 Mistral 7B v0.2 (Uncensored) 🐬DictaLM 2.0 Instruct 🇮🇱

Llama 2 7B Based Models

For iPhones/iPads with 6GB+ RAM

Airoboros l2 7b 3.0 Spicyboros 7b 2.2 🌶️

Phi-2 3B Based Models

For iPhones/iPads with 4GB+ RAM

Phi-2 Orange 🍊Dolphin 2.6 Phi-2 (Uncensored) 🐬Phi-2 Super 🤖Phi-2 Orange v2 🍊

H2O Danube Based Models

For iPhones/iPads with 4GB+ RAM

H2O Danube 1.8B Chat

StableLM 3B Based Models

For iPhones/iPads with 4GB+ RAM

StableLM 2 Zephyr 1.6B 🪁Nous-Capybara-3B V1.9 Rocket 3B 🚀

TinyLlama 1.1B Based Models

For iPhones/iPads with 4GB+ RAM

TinyLlama 1.1B Chat 🦙TinyDolphin 2.8 1.1B Chat 🐬

Yi 6B Based Models

For iPhones/iPads with 6GB+ RAM

Yi 6B Chat 🇨🇳

macOS

DeepSeek R1 Distill Based Models

For Apple Silicon Macs with 16GB+ RAM

DeepSeek R1 Distill Llama 8B DeepSeek R1 Distill Llama 8B Abliterated (Uncensored)DeepSeek R1 Distill Qwen 7B DeepSeek R1 Distill Qwen 14B

DeepSeek R1 Distill Based Models

For Apple Silicon Macs with 32GB+ RAM

Fuse O1 DeepSeek R1 QwQ SkyT1 32B DeepSeek R1 Distill Qwen 32B Abliterated (Uncensored)

DeepSeek R1 Distill Based Models

For Apple Silicon Macs with 48GB+ RAM

DeepSeek R1 Distill Llama 70B

Phi-4 14B Based Models

For Apple Silicon Macs with 16GB+ RAM

Phi-4

Meta Llama 3.3 70B Based Models

For Apple Silicon Macs with 48GB+ RAM

Meta Llama 3.3 70B Instruct 🦙Llama 3.3 70B Instruct Abliterated (Uncensored)EVA LLaMA 3.33 70B v0.0 (Role-Play/Story Writing)Llama 3.3 70B Euryale v2.3 (Role-Play/Story Writing)

Meta Llama 3.2 3B Based Models

For Apple Silicon Macs with 8GB+ RAM

Meta Llama 3.2 3B Instruct 🦙Llama 3.2 3B Instruct Abliterated 🦙 (Uncensored)Llama 3.2 3B Instruct Uncensored 🦙Hermes 3 Llama 3.2 3B FuseChat Llama 3.2 3B Instruct

Meta Llama 3.2 1B Based Models

For Apple Silicon Macs with 8GB+ RAM

Meta Llama 3.2 1B Instruct 🦙Llama 3.2 1B Instruct Abliterated 🦙 (Uncensored)FuseChat Llama 3.2 1B Instruct

Meta Llama 3.1 70B Based Models

For Apple Silicon Macs with 64GB+ RAM

Meta Llama 3.1 70B Instruct 🦙

Meta Llama 3.1 8B Based Models

For Apple Silicon Macs with 8GB+ RAM

Meta Llama 3.1 8B Instruct 🦙Meta Llama 3.1 8B Instruct Abliterated 🦙(Uncensored)Hermes 3 Llama 3.1 8B FuseChat Llama 3.1 8B Instruct Llama 3.1 8B Lexi Uncensored V2 (Therapist)

Qwen 2.5 Based Models

For Apple Silicon Macs with 8GB+ RAM

Qwen 2.5 0.5B Unquantized Qwen 2.5 1.5B Qwen 2.5 3B Qwen 2.5 7B Qwen 2.5 Coder 0.5B Unquantized Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 3B Qwen 2.5 Coder 7B FuseChat Qwen 2.5 7B Instruct EVA-D Qwen2.5 1.5B v0.0 (Role-Play/Story Writing)EVA Qwen2.5 7B v0.1 (Role-Play/Story Writing)

Qwen 2.5 14B Based Models

For Apple Silicon Macs with 16GB+ RAM

Qwen 2.5 Coder 14B EVA Qwen2.5 14B v0.2 (Role-Play/Story Writing)

Qwen 2.5 32B Based Models

For Apple Silicon Macs with 24GB+ RAM

Qwen 2.5 32B Qwen 2.5 Coder 32B EVA Qwen2.5 32B v0.2 (Role-Play/Story Writing)

Google Gemma 2 9B Based Models

For Apple Silicon Macs with 16GB+ RAM

Gemma-2 9B IT 💎Gemma-2 9B IT SPPO Iter3 Tiger Gemma 9B v3 🐅 (Uncensored)FuseChat Gemma 2 9B Instruct

Google Gemma 2 2B Based Models

For Apple Silicon Macs with 8GB+ RAM

Gemma-2 2B IT 💎SauerkrautLM Gemma-2 2B IT

Meta Llama 3 70B Based Models

For Apple Silicon Macs with 48GB+ RAM

Meta Llama 3 70B Instruct 🦙Smaug Llama 3 70B Instruct Smaug Llama 3 70B Instruct Abliterated v3 (Uncensored)Cat Llama 3 70B Instruct

Meta Llama 3 8B Based Models

For Apple Silicon Macs with 8GB+ RAM

Phi-3 Mini 3.8B Based Models

For Apple Silicon Macs with 8GB+ RAM

Phi-3 Mini 4K Instruct Kappa-3 Phi Abliterated (Uncensored)

Google Gemma Based Models

For Apple Silicon Macs with 8GB+ RAM

Gemma 2B IT 💎Gemma 1.1 2B IT 💎

Mixtral 8x7B Based Models

For Apple Silicon Macs with 32GB+ RAM

Mixtral-8x7B-Instruct-v0.1 Dolphin 2.6 Mixtral 8x7B 🐬Nous Hermes 2 Mixtral 8x7B DPO ☤

Llama 33B Based Models

For Apple Silicon Macs with 24GB+ RAM

WizardLM 33B v1.0 (Uncensored)

Llama 2 13B Based Models

For Apple Silicon Macs with 16GB+ RAM

Wizard LM 13B Spicyboros 13B 🌶️Synthia 13B 1.2 XWin-LM-13B Mythomax L2 13B

CodeLlama 13B Based Models

For Apple Silicon Macs with 16GB+ RAM

WhiteRabbitNeo-13B-v1

Llama 2 7B Based Models

For Apple Silicon Macs with 8GB+ RAM

airoboros-l2-7b-3.0 Spicyboros 7b 2.2 🌶️Xwin-LM-7B v0.1

Solar 10.7B Based Models

For Apple Silicon Macs with 16GB+ RAM

Nous-Hermes-2-SOLAR-10.7B ☤

Phi-2 3B Based Models

For Apple Silicon Macs with 8GB+ RAM

Phi-2 Orange 🍊Phi-2 Orange Version 2 🍊Dolphin 2.6 Phi-2 (Uncensored) 🐬

StableLM 3B Based Models

For Apple Silicon Macs with 8GB+ RAM

StableLM Zephyr 3B 🪁

Yi 6B Based Models

For Apple Silicon Macs with 8GB+ RAM

Yi 6B Chat 🇨🇳

Yi 34B Based Models

For Apple Silicon Macs with 24GB+ RAM

Yi 34B Chat 🇨🇳

How Can We Help?

Whether you've got a question or you're facing an issue with Private LLM, we're here to help you out. Just drop your details in the form below, and we'll get back to you as soon as we can.