archives/edge-gallery
archives/edge-gallery
2
0
Fork 0
mirror of https://github.com/google-ai-edge/gallery.git synced 2025-07-08 15:40:31 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.
25 commits 7 branches 11 tags 1.6 MiB
Find a file
Jing Jin 73f7dfeb63
Update README.md
2025-05-19 14:02:15 -07:00
Android - Better text formatting on home screen for smaller screen. 2025-05-19 11:44:00 -07:00
.gitignore Initial checkin 2025-04-14 16:42:40 -07:00
CONTRIBUTING.md Initial checkin 2025-04-14 16:42:40 -07:00
LICENSE Initial checkin 2025-04-14 16:42:40 -07:00
model_allowlist.json Update model_allowlist.json 2025-05-19 11:32:13 -07:00
README.md Update README.md 2025-05-19 14:02:15 -07:00

README.md

Google AI Edge Gallery ✨

License GitHub release (latest by date)

Explore, Experience, and Evaluate the Future of On-Device Generative AI with Google AI Edge.

The Google AI Edge Gallery is an experimental app that puts the power of cutting-edge Generative AI models directly into your hands, running entirely on your Android (available now) and iOS (coming soon) devices. Discover what's possible, today!

🚀 What is Google AI Edge Gallery?

Google AI Edge Gallery is your interactive playground for on-device AI. It's built to:

  • Inspire Developers: See what you can build with Google AI Edge.
  • Showcase Capabilities: Experience the performance and quality of LiteRT-optimized models.
  • Reduce Friction: Easily try out different models and tasks without writing code.
  • Foster Community: An open-source project for learning.

✨ Core Features

  • 📱 On-Device GenAI: Run LLMs locally – fast, private, and offline-capable.
  • 🤖 Diverse Model Zoo: Explore models from the Hugging Face LiteRT Community and Google.
  • ✍️ Prompt Lab: Summarize, rewrite, generate code, or use freeform prompts to explore single-turn LLM use cases.
  • 💬 AI Chat: Engage in multi-turn conversations.
  • 📊 Performance Insights: Real-time benchmarks (TTFT, decode speed, latency).
  • 🧩 Bring Your Own Model: Test your local LiteRT .task models.
  • 🔗 Developer Resources: Quick links to model cards and source code.

🏁 Get Started in Minutes!

  1. Download the App: Grab the latest APK.
  2. Install & Explore: For detailed installation instructions (including for corporate devices) and a full user guide, head over to our Project Wiki!

🛠️ Technology Highlights

  • Google AI Edge: Core APIs and tools for on-device ML.
  • LiteRT: Lightweight runtime for optimized model execution.
  • LLM Inference API: Powering on-device Large Language Models.
  • Hugging Face Integration: For model discovery and download.

🤝 Feedback

This is an experimental Alpha release, and your input is crucial!

📄 License

Licensed under the Apache License, Version 2.0. See the LICENSE file for details.

🔗 Useful Links