Private LLM - Local AI Chatbot 17+

Secure Private AI Chatbot

Numen Technologies Limited

    • 4.5 • 4 Ratings
    • 9,99 €

Description

Now with Llama 3.2 1B, Llama 3.2 3B and Gemma 2 9B based models.

Meet Private LLM: Your Secure, Offline AI Assistant for macOS

Private LLM brings advanced AI capabilities directly to your iPhone, iPad, and Mac—all while keeping your data private and offline. With a one-time purchase and no subscriptions, you get a personal AI assistant that works entirely on your device.

Key Features:

- Local AI Functionality: Interact with a sophisticated AI chatbot without needing an internet connection. Your conversations stay on your device, ensuring complete privacy.

- Wide Range of AI Models: Choose from various open-source LLM models like Llama 3.2, Llama 3.1, Google Gemma 2, Microsoft Phi-3, Mistral 7B, and StableLM 3B. Each model is optimized for iOS and macOS hardware using advanced OmniQuant quantization, which offers superior performance compared to traditional RTN quantization methods.

- Siri and Shortcuts Integration: Create AI-driven workflows without writing code. Use Siri commands and Apple Shortcuts to enhance productivity in tasks like text parsing and generation.

- No Subscriptions or Logins: Enjoy full access with a single purchase. No need for subscriptions, accounts, or API keys. Plus, with Family Sharing, up to six family members can use the app.

- AI Language Services on macOS: Utilize AI-powered tools for grammar correction, summarization, and more across various macOS applications in multiple languages.

- Superior Performance with OmniQuant: Benefit from the advanced OmniQuant quantization process, which preserves the model's weight distribution for faster and more accurate responses, outperforming apps that use standard quantization techniques.

Supported Model Families:

- Llama 3.2 Based Models
- Llama 3.1 Based Models
- Phi-3 Based Models
- Google Gemma 2 Based Models
- Mixtral 8x7B Based Models
- CodeLlama 13B Based Models
- Solar 10.7B 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 privatellm.app/models.

Private LLM is a better alternative to generic llama.cpp and MLX wrappers apps like Ollama, LLM Farm, LM Studio, RecurseChat, etc on three fronts:
1. Private LLM uses a faster mlc-llm based inference engine.
2. All models in Private LLM are quantised using the state of the art OmniQuant quantization algorithm, while competing apps use naive round-to-nearest quantization.
3. Private LLM is a fully native app built using C++, Metal and Swift, while many of the competing apps are (bloated) Electron based apps.

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.

What’s New

Version 1.9.2

- Bugfix release: fix for crash while loading some of the older models that use the sentencepiece tokenizer.
- Drop support for Llama 3.2 1B and 3B models on Intel Macs due to stability issues.

Thank you for choosing Private LLM. We are committed to continue improving the app and to making it more useful for you. For support requests and feature suggestions, please feel free to email us at support@numen.ie, or tweet us @private_llm. If you enjoy the app, leaving an App Store is a great way to support us.

Ratings and Reviews

4.5 out of 5
4 Ratings

4 Ratings

Sinoviale ,

Dare la possibilità di caricare un modello personale

Your application is paid, but it should allow users to upload their own personal model via file. I use Llama3, 4Q, which works everywhere, while your model does not function correctly as it responds without understanding. You have only provided Llama3, 3Q. We request that you add a feature to select and upload a GGUF file that we have already downloaded.

Developer Response ,

One of the reasons why our app is far better than other GGUF based apps is because we quantize models with the state of the art OmniQuant algorithm. It takes many hours of NVIDIA GPU time to quantize each model with OmniQuant, while it only takes a few minutes of CPU time to RTN quantize GGUF models. But the resulting OmniQuant quantized models are superior to RTN quantized models, in terms of perplexity. You'll find more details about this on our website (privatellm.app). If you have any requests for models, please write to us and we'll quantize and include the option to download it in an upcoming release.

dbenji83 ,

Missing Shortcuts repository and extensions

I purchased also for the idea of having a repository for shortcuts and extensions to lunch the Private LLM directly from Finder or inside a document. It's incomplete without that functionality. It would be nice to have the following "extensions" directly in Finder:
- analyze the document
- summerize document
- chat with the document
and inside the file
- translate
- summerize the text
- rephase
- elaborate

Last but not least it would be nice to add the DocsGPT model and the possibility of dragging an drop one or more document directly in the Private LLM app.

Developer Response ,

Thanks for the review! We don't ship any shortcuts with the app, but you can download popular user contributed shortcuts from our website (privatellm.app). Also, we have macOS services for bulletizing text, grammar correction, rephrasing and shortening text. You can right click on editable text within any app and access them from the services sub-menu. Additionally, users can also assign keyboard shortcuts to these services from System Settings -> Keyboard -> Keyboard Shortcuts -> Services -> Text. Also, users can add their own services for translation, or anything else they'd like to wish for by creating a macOS Shortcut that uses Private LLM and checking the checkbox within the Shortcuts app to make it accessible from the Services menu. Finally, We're working on implementing Retrieval augmented generation (RAG). As you know, given our commitment to privacy, we need to implement completely on-device and there are some technical challenges that need to be overcome before we can ship that feature. If you have any feature requests, please feel free to email us (support@numen.ie) or DM us on Twitter (@private_llm) or join our Discord.

App Privacy

The developer, Numen Technologies Limited, indicated that the app’s privacy practices may include handling of data as described below. For more information, see the developer’s privacy policy.

Data Not Collected

The developer does not collect any data from this app.

Privacy practices may vary based on, for example, the features you use or your age. Learn More

Supports

  • Family Sharing

    Up to six family members can use this app with Family Sharing enabled.

You Might Also Like

MLC Chat
Productivity
YourChat
Productivity
PocketGPT: Private AI
Productivity
Local Brain
Productivity
Hugging Chat
Productivity
PocketPal AI
Productivity