Private LLM - Local AI Chatbot 17+

Numen Technologies Limited

    • 4,8 • Оценок: 6
    • 899,00 ₽

Снимки экрана

Описание

Discover Private LLM, your secure, private AI assistant for iPhone, iPad, and macOS. Designed to boost your productivity and creativity while ensuring your privacy, Private LLM is a one-time purchase offering a universe of AI capabilities without subscriptions. Our chatbot utilizes cutting-edge on-device AI to keep your interactions confidential and completely offline, compatible with all your Apple devices.

Why Choose Private LLM?

- Diverse AI Models at Your Command: Select from a wide array of open-source LLM model families such as Google Gemma 2B, Mixtral 8x7B, Mistral 7B, Llama 2 (7B, 13B, and 33B), CodeLlama 13B, Solar 10.7B, and Phi 2 3B. Customize your AI experience for creative brainstorming, coding assistance, or daily inquiries.

- Seamless Siri & Shortcuts Integration: Enhance your AI interactions with Siri commands and customizable Shortcuts, making your digital assistant more integrated and accessible within your Apple ecosystem.

- Customizable System Prompts: Fine-tune your AI's responses and interactions to your liking with customizable system prompts, catering to your specific needs and preferences.

- Complete Privacy and Security: Private LLM confines your conversations to your device, providing unparalleled privacy. Our on-device AI enables powerful computing without data compromise or the need for an internet connection.

- Family Sharing & Offline Functionality: A one-time purchase that supports Family Sharing. Download models as needed and enjoy full AI assistant functionality, even offline.

- System Wide Grammar Correction and Summarization: Offering grammar correction, summarization, text shortening, and rephrasing within any app on your Mac.

Private LLM is more than a chatbot; it's an all-encompassing AI companion that respects your privacy while offering versatile, on-demand assistance. Whether for creative writing, solving complex programming issues, or general inquiries, Private LLM adapts to your needs, ensuring your data remains secure and on your device. Embark on a journey with Private LLM today and elevate your productivity and creative projects with the most private AI assistant for macOS and iOS devices.

Leveraging state-of-the-art Omniquant quantized models, Private LLM is a native Mac app that surpasses others with superior text generation, faster performance, and deeper integration compared to apps using generic baseline RTN quantized models like Ollama and LMStudio.

Supported Model Families:

- Google Gemma Based Models
- Mixtral 8x7B Based Models
- Llama 33B Based Models
- Llama 2 13B Based Models
- CodeLlama 13B Based Models
- Llama 2 7B Based Models
- Solar 10.7B Based Models
- Phi 2 3B Based Models
- Mistral 7B Based Models
- StableLM 3B Based Models
- Yi 6B Based Models
- Yi 34B Based Models

For a full list of supported models, including detailed specifications, please visit our website.

Optimized for Apple Silicon Macs with the Apple M1 chip or later, Private LLM for macOS delivers the best performance. Users on older Intel Macs without eGPUs may experience reduced performance.

Что нового

Версия 1.8.7

- Support for downloading a 3-bit OmniQuant quantized version of the Meta-Llama-3-70B-Instruct model on Apple Silicon Macs with 48GB or more RAM.
- Stability improvements and bug fixes.

If you have any feedback or questions, we'd love to hear from you! Numen Technologies offers free tech support; you can email: support@numen.ie, message us on our Discord, or Tweet at us @private_llm. If you find Private LLM to be useful, we'd appreciate a review on the App Store. Your review will help other people find Private LLM.

Оценки и отзывы

4,8 из 5
Оценок: 6

Оценок: 6

ParamonSaurik ,

Шикарно

Добавьте выбор любой модели - и будет вообще супер. Огромное спасибо за вашу работу. Отлично работает на iphone и mac. Единственное, что представленные модели очень плохо работают с русским языком. Еще раз спасибо за то, что вы делаете)

George An. ,

Poor support of iOS and several other problems

First, I have an iPhone 14 Pro, and the app has layout issues. There's no option to save temperature for next launch. Opening llama 3 will crash the app. Shortcuts functionality is poor, as it doesn't allow custom system prompts only queries. Also, executing a shortcut function opens the app instead of quietly running in the background. Fixing these issues would instantly make this review a 5-star one

Ответ разработчика ,

Thanks for the review! Unfortunately, the Llama 3 8B model just barely fits in the iPhone 14 Pro's 6GB RAM. And this doesn't work if there are other memory hungry apps running in the background. We recommend using devices with 8GB or more RAM to run it. We decided to let users try it and decide for themselves, based on the feedback we got from our beta testers. I'd recommend trying any of the Llama 2 7B or Mistral 7B models. Also, the new Phi-3-Mini model. Regarding executing shortcut functions in the background, this is an iOS limitation. For performance reasons, iOS and tvOS do not let background apps use the GPU. macOS does not have this limitation, and consequently, the macOS version of the app runs perfectly fine in the background when invoked from Shortcuts.

Kai SD ,

Model downloading is misleading

The app is shipped with RedPajamas 3B model, and it offers to download an unnamed 7B model, but if you refuse or close the app until the download is completed, it won’t offer it ever again until you completely reinstall the app. Model selection and download seems to be supported only on MacOS version, regardless of what written in patch notes and on the website. Sad, because i was really hoping to try Phi-3 on iOS.

Ответ разработчика ,

Hey, thanks for the review. Your review seems to indicate that you're still using version 1.6.7 of the app, which was released more than 4 months ago. Please upgrade the app. It now supports downloading up to a little over 2 dozen models (depending on device capabilities). Support for downloading multiple models was added in version 1.7.0 of the app, which was released over a month ago. Support for Phi-3-mini was released in version 1.8.1 (the latest version), two days ago. Phi-3-mini works on all devices with 6GB or more RAM.

Конфиденциальность приложения

Разработчик Numen Technologies Limited указал, что в соответствии с политикой конфиденциальности приложения данные могут обрабатываться так, как описано ниже. Подробные сведения доступны в политике конфиденциальности разработчика.

Сбор данных не ведется

Разработчик не ведет сбор данных в этом приложении.

Конфиденциальные данные могут использоваться по-разному в зависимости от вашего возраста, задействованных функций или других факторов. Подробнее

Поддерживается

  • Семейный доступ

    При включенном Семейном доступе приложением могут пользоваться до шести членов «Семьи».

Вам может понравиться

YourChat
Производительность
Local Brain
Производительность
MLC Chat
Производительность
Private LLM - Offline AI
Производительность
Vanessa LLM
Производительность
Patagonia AI - Private LLM
Производительность