Presentation: On-device LLM with Gemini Nano

I recently gave a talk at a local meetup, MelbJS.

Talk was about my explorations with the Google Chrome Built-in AI early preview.

I’ve embedded the slides below, which are done as an interactive notebook using the very cool Slides on Observable.

If you follow the instructions and have the model setup and ready to use in either Chrome Dev or Chrome Canary the interactive parts in the slides will work, otherwise nothing will happen.

1. **Install Chrome Dev**: Ensure you have version 127. Download Chrome Dev.
2. Check that you’re on 127.0.6512.0 or above
3. Enable two flags:
   • chrome://flags/#optimization-guide-on-device-model - BypassPerfRequirement
   • chrome://flags/#prompt-api-for-gemini-nano - Enabled
4. Relaunch Chrome
5. Navigate to chrome://components
6. Check that Optimization Guide On Device Model is downloading or force download if not Might take a few minutes for this component to even appear
7. Open dev tools and type (await ai.languageModel.capabilities()).available, should return "readily" when all good