Google AI Edge Gallery

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

What is Google AI Edge Gallery?

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. Dive into a world of creative and practical AI use cases, all running locally, without needing an internet connection once the model is loaded. Experiment with different models, chat, ask questions with images, explore prompts, and more!

Key Features

• 📱 Run Locally, Fully Offline: Experience the magic of GenAI without an internet connection. All processing happens directly on your device.
• 🤖 Choose Your Model: Easily switch between different models from Hugging Face and compare their performance.
• 🖼️ Ask Image: Upload an image and ask questions about it. Get descriptions, solve problems, or identify objects.
• ✍️ 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.

How to Download and Install Google AI Edge Gallery App?

Step 1: Download the latest Google AI Edge Gallery APK from the given link.

Step 2: Once the APK is downloaded to your device (e.g., in your “Downloads” folder), open your device’s file manager.

Step 3: Locate and tap on the “ai-edge-gallery.apk” file to install.

Step 4: You may be prompted to allow installations from “Unknown Sources” If so, enable this permission (usually in your device’s settings under “Security” or “Apps”). The system will guide you.

Step 5: Confirm the installation. ( If you are looking for Installation via ADB, then check this detailed guide. )

Step 6: Once the application is installed on your Android phone, you will be prompted to the Home Screen: Here you will be greeted by a grid of AI capabilities (e.g., “Prompt Lab”, “AI Chat”, “Ask Image”). Tap on a capability to explore it.

Step 7: After selecting a capability, you’ll see a list of compatible models. You can download new models “Gemma-3n-E2B-it-int4” by clicking on the Download & Try button or try ones already on your device.

Step 8: After that, you will move to the Task Interface, where you can interact with the model. It varies by task (e.g., text input for chat, image picker for image-supported models).

Step 9: At last, you can navigate to the “Settings/Parameters” section, where you can often adjust model inference parameters (like switch between CPU and GPU, set temperature, etc) for different tasks.

Interface Photos/Images

Troubleshooting Tips

• App Crash: Try restarting the app. If persistent, please contact us and with steps to reproduce.
• Model Download Failure: Check your network connectivity. Ensure HF login (if required for the model) was successful and terms were accepted.
• Slow Performance: Performance varies by device hardware and model size. The stats shown are specific to your device.
• HF Login Issues: Ensure correct credentials. If issues persist with HF, you might need to check their platform status.
• Local Model Import Issues:
  • Ensure the model is in the correct /sdcard/Download/ folder.
  • Verify the .task file is not corrupted and is LiteRT compatible.

Popular FAQs