Private LLM Secure, Private AI Chatbot That Works Locally on Your iPhone, iPad and Mac

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 opens the door to the vast possibilities of AI with support for an extensive selection of open-source LLM models, including the Llama 3, Google Gemma, Microsoft Phi-2, Mixtral 8x7B family and many more on both your iPhones, iPads and Macs. This wide range of model support ensures that users on iOS, iPadOS, and macOS can fully utilize the power of AI, customized specifically for their devices.
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.
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.

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.
Screenshot of Private LLM running 4-bit OmniQuant quantised Mixtral 8x7B Instruct model, with the Sally prompt.
Screenshot of LMStudio running Q8_0 quantised Mixtral 8x7B Instruct model, with the Sally prompt.

See what our users say about us on the App Store

Remarkably good app, very active developer
by Conventional Dog-Apr 7, 2024

Possibly the single best app purchase I've ever made. The developer is constantly improving it and talking with users on Discord and elsewhere. One price includes Mac, iPhone, and iPad versions (with family sharing). Mac shortcuts can be used to create what amount to custom GPTs. (There's even a user-contributed, quite clever bedtime story generator on the website.) The 10.7B-parameter SOLAR LLM (one of many included) running on my 16 GB M1 MacBook Air gives me fast responses that are subjectively almost on the level of GPT-3.5. For something running completely locally with full privacy, it's remarkable. More RAM allows an even larger choice of language models. But the tiniest model running on my iPhone 12 Pro is usable. (Tip: Experiment with changing the system prompt to fine-tune it for your purposes.)

Version 1.8.3|United States

Download the Best Open Source LLMs

macOS

Google Gemma Based Models

All Intel and Apple Silicon Macs
Gemma 2B IT 💎Gemma 1.1 2B IT 💎

Mixtral 8x7B Based Models

Apple Silicon Macs with at least 32GB of RAM
Mixtral-8x7B-Instruct-v0.1Dolphin 2.6 Mixtral 8x7B 🐬Nous Hermes 2 Mixtral 8x7B DPO

Llama 33B Based Models

Apple Silicon Macs with at least 24GB of RAM
WizardLM 33B v1.0 Uncensored

Llama 2 13B Based Models

Apple Silicon Macs with at least 16GB of RAM
Wizard LM 13BSpicyboros 13B 🌶️Synthia 13B 1.2XWin-LM-13BMythomax L2 13B

CodeLlama 13B Based Models

Apple Silicon Macs with at least 16GB of RAM
WhiteRabbitNeo-13B-v1

Llama 2 7B Based Models

All Intel and Apple Silicon Macs
airoboros-l2-7b-3.0Spicyboros 7b 2.2 🌶️Xwin-LM-7B v0.1

Solar 10.7B Based Models

Apple Silicon Macs with at least 16GB of RAM
Nous-Hermes-2-SOLAR-10.7B

Phi 2 3B Based Models

All Intel and Apple Silicon Macs
Phi-2 Orange 🍊Phi-2 Orange Version 2 🍊Dolphin 2.6 Phi-2 🐬

StableLM 3B Based Models

All Intel and Apple Silicon Macs
StableLM Zephyr 3B 🪁

Yi 6B Based Models

All Intel and Apple Silicon Macs
Yi 6B Chat 🇨🇳

Yi 34B Based Models

Apple Silicon Macs with at least 24GB of RAM
Yi 34B Chat 🇨🇳
iOS

Llama 3 8B Based Models

on devices with 6GB or more RAM
Llama 3 8B Instruct 🦙Dolphin 2.9 Llama 3 8B Uncensored 🐬

Google Gemma Based Models

on devices with 8GB or more RAM
Gemma 2B IT 💎Gemma 1.1 2B IT 💎

Llama 2 7B Based Models

on devices with 6GB or more RAM
Airoboros l2 7b 3.0Spicyboros 7b 2.2 🌶️

Phi 2 3B Based Models

on devices with 4GB or more RAM
Phi-2 Orange 🍊Dolphin 2.6 Phi-2 🐬Phi-2 Super 🤖Phi-2 Orange v2 🍊

H2O Danube Based Models

on all devices
H2O Danube 1.8B Chat

StableLM 3B Based Models

on devices with 4GB or more RAM
StableLM 2 Zephyr 1.6B 🪁Nous-Capybara-3B V1.9Rocket 3B 🚀

TinyLlama 1.1B Based Models

on all devices
TinyLlama 1.1B Chat 🦙TinyDolphin 2.8 1.1B Chat 🐬

Yi 6B Based Models

on devices with 6GB or more RAM
Yi 6B Chat 🇨🇳
Community-Crafted Shortcuts

Explore shortcuts created by users who've transformed their daily routines using Private LLM. Feeling inspired? Share your own shortcut masterpiece with us through the contact form.

Frequently Asked Questions
  • Private LLM is your private AI chatbot, designed for privacy, convenience, and creativity. It operates entirely offline on your iPhone, iPad, and Mac, ensuring your data stays secure and confidential. Private LLM is a one-time purchase on the App Store, allowing you unlimited access without any subscription fees. nb: We hate subscriptions, and we aren’t hypocrites to subject our users to what we hate.

  • Private LLM works offline and uses a decoder only transformer (aka GPT) model that you can casually converse with. It can also help you with summarising paragraphs of text, generating creative ideas, and provide information on a wide range of topics.

  • Absolutely not. Private LLM is dedicated to ensuring your privacy, operating solely offline without any internet access for its functions or accessing real-time data. An internet connections is only required when you opt to download updates or new models, during which no personal data is collected or transmitted, exchanged or collected. Our privacy philosophy aligns with Apple's stringent privacy and security guidelines, and our app upholds the highest standards of data protection. It's worth noting that, on occasion, users might inquire if Private LLM can access the internet, leading to potential model hallucinations suggesting it can. However, these responses should not be taken as factual. If users would like to independently verify Private LLM’s privacy guarantees, we recommend using network monitoring tools like Little Snitch. This way, you can see for yourself that our app maintains strict privacy controls. For those interested in accessing real-time information, Private LLM integrates seamlessly with Apple Shortcuts, allowing you to pull data from RSS feeds, web pages, and even apps like Calendar, Reminders, Notes and more. This feature offers a creative workaround for incorporating current data into your interactions with Private LLM, while still maintaining its offline privacy-first ethos. If you have any questions or need further clarification, please don't hesitate to reach out to us.

  • Firstly, Private LLM stands out from other local AI solutions through its advanced model quantization technique known as OmniQuant. Unlike the naive Round-To-Nearest (RTN) quantization used by other competing apps, OmniQuant quantization is an optimization based method that uses learnable weight clipping. This method allows for a more precise control over the quantization range, effectively maintaining the integrity of the original weight distribution. As a result, Private LLM achieves superior model performance and accuracy, nearly matching the performance of an un-quantized 16 bit floating point (fp16) model, but with significantly reduced computational requirements at inference time.

    While the process of quantizing models with OmniQuant is computationally intensive, it's a worthwhile investment. This advanced approach ensures that the perplexity (a measure of model's text generation quality) of the quantized model remains much closer to that of the original fp16 model than is possible with the naive RTN quantization. This ensures that Private LLM users enjoy a seamless, efficient, and high-quality AI experience, setting us apart other similar applications.

    Secondly, unlike almost every other competing offline LLM app, Private LLM isn’t based on llama.cpp. This means advanced features that aren’t available in llama.cpp (and by extension apps that use it) like attention sinks and sliding window attention in Mistral models are available in Private LLM, but unavailable elsewhere. This also means that our app is significantly faster than competition on the same hardware (YouTube videos comparing performance).

    Finally, we are machine learning engineers and carefully tune quantization and parameters in each model to maximize the text generation quality. For instance, we do not quantize the embeddings and gate layers in Mixtral models because quantizing them badly affects the model’s perplexity (needless to mention, our competition naively quantize everything). Similarly with the Gemma models, quantizing the weight tied embeddings hurts the model’s perplexity, so we don’t (while our competitors do).

    By prioritizing accuracy and computational efficiency without compromising on privacy and offline functionality, Private LLM provides a unique solution for iOS and macOS users seeking a powerful, private, and personalized AI experience.

  • After a one-time purchase, you can download and use Private LLM on all your Apple devices. The app supports Family Sharing, allowing you to share it with your family members.

  • Unlike almost all other AI chatbot apps that are currently available, Private LLM operates completely offline and does not use an external 3rd party API, ensuring your data privacy. There's no tracking or data sharing. Your data stays on your device. Plus, it's a one-time purchase, giving you lifetime access without having to worry about recurring subscription fees.

  • Private LLM can analyse and summarise lengthy paragraphs of text in seconds. Just paste in the content, and the AI will generate a concise summary, all offline. You could also use Private LLM for rephrasing and paraphrasing with prompts like:

    • Give me a TLDR on this: [paste content here]
    • You’re an expert copywriter. Please rephrase the following in your own words: [paste content]
    • Paraphrase the following text so that it sounds more original: [paste content]
  • Absolutely! Private LLM can generate insightful suggestions and ideas, making it a powerful tool for brainstorming and problem-solving tasks. Here are some example brainstorming prompts that you can try asking Private LLM. Please feel free to experiment and try out your own prompts.

    • Can you give me some potential themes for a science fiction novel?
    • I’m planning to open a vegan fast-food restaurant. What are the weaknesses of this idea?
    • I run a two year old software development startup with one product that has PMF, planning on introducing a new software product in a very different market. Use the six hats method to analyse this.
    • Utilise the Golden Circle Model to create a powerful brand for a management consulting business.
  • Sampling temperature and Top-P are universal inference parameters for all autoregressive causal decoder only transformer (aka GPT) models, and are not specific to Private LLM. The app has them set to reasonable defaults (0.7 for Sampling temperature and 0.95 for Top-p), But you can always tweak them and see what happens. Please bear in mind that changes to these parameters do not take effect until the app is restarted.

    These parameters control the tradeoff between deterministic text generation and creativity. Low values lead to boring but coherent response, higher values lead to creative but sometimes incoherent responses.

  • Yes. Private LLM has two app intents that you can use with Siri and the Shortcuts app. Please look for Private LLM in the Shortcuts app. Additionally, Private LLM also supports the x-callback-url specification which is also supported by Shortcuts and many other apps. Here’s an example shortcut using the x-callback-url functionality in Private LLM.

  • Private LLM is performing on-device inference on a large language model, which is a memory-intensive process. The iOS operating system sends the app a memory warning; and not acting on the warning will lead to iOS terminating the app. In the interest of stability, the app immediately stops generating text. If you're running several apps simultaneously or your device has limited memory, you might receive a memory warning. Closing unused apps in the background and/or restarting the app device can often resolve this.

  • This could be due to the device running low on memory, or if the task given to Private LLM is particularly complex. In such cases, consider closing memory hungry apps that might be running in the background and try breaking down the request into smaller, more manageable tasks for the LLM to process. In the latter case, simply responding with “Continue”, “Go on” or “Tell me” also works.

  • We’re sorry to hear you’re considering a refund. You can request a refund through the Apple App Store. Simply navigate to your Apple account's purchase history, find Private LLM, and click on 'Report a Problem' to initiate the refund process. We would also love to hear from you about how we can improve. Please reach out to us with your feedback.

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.