Private AI

FireEdge

In-app purchases

About this app

Transform your Android device into a powerful, secure AI companion. Run advanced language models directly on your phone, ensuring complete data privacy and offline functionality.

Key Features:

Offline AI: Chat with AI models without an internet connection
Privacy-First: All processing stays on your device, zero data collection
Multiple LLMs: Choose from a wide range of built-in models
Customizable: Premium users can add any GGUF model file
Chat History: Searchable conversations for easy reference
No Ads: Clean, distraction-free interface

Built-in Models:

Gemma 2 (Default): Google's lightweight, state-of-the-art model for various text generation tasks
Llama 3.2: Advanced model for diverse language tasks
Phi-3.5 mini: Microsoft's lightweight model with strong reasoning capabilities
Orca mini: General-purpose model suitable for entry-level hardware
Rocket 3B: Compact model with outstanding performance in benchmarks
Mistral: High-performance open-source model
NeuralBeagle: Cutting-edge model excelling in instruction following and reasoning
OpenHermes: Versatile assistant with improved code generation capabilities
WizardLM: Advanced language model with broad capabilities, trained without alignment constraints
Silicon Maid: Specialized model for creative and role-playing tasks

Premium Feature:

Model Flexibility: Add any compatible GGUF model file to tailor the AI experience to your specific needs

Unlock the full potential of AI while maintaining complete control over your data. Whether you're a privacy enthusiast, a tech professional, or simply curious about AI, our app offers a secure and powerful on-device AI experience.
Download now and start chatting with advanced AI models, all while keeping your conversations truly private!
Note: Uncensored models have no guardrails. Users are responsible for any content generated or actions taken with the models.
Shout out to the open source AI/ML community for their invaluable contributions!

Ratings and reviews

The user interface could use a little work. I would love it if they added a space to add a PDF file. Enjoyable product great read back. would love the option to choose different voices even if it was a paid option. I like the fact that I can use other models in upload. Absolutely worth the download if you're playing with private artificial intelligence building.

I have a problem, it always says "Model failed to load" even though I have enough RAM and disk space. I have tried all the free models and they all have the same error, I have also reinstalled the app multiple times. Please help. EDIT: The developers suggestion didn't work, but I'm pretty sure it's because of my device. I'll try the app again when I get a new phone which should be soon. Until then I'll give it three stars.

Pretty solid basic app for local ai. The addition of something like JSON file save and load would be appreciated, or some other way of reloading the chat - when I leave to use other apps and come back sometimes previous chat is there, sometimes not, and not the best way of reloading. That said it's easy to use (much easier than the termux method), and easy to add other gguf models. Slower than pc, obvs, but useable. It's a boon for creative writing and creating characters or just general facts

What’s new

llama.cpp update