Hands-on Workshop - On-device AI with Gemma 4
The Gemma family of models crossed 1 billion downloads in August 2026! The latest in the series, Gemma 4, is designed to run locally on phones, laptops and other edge devices, providing lower latency, greater privacy, reduced costs, and independence from cloud inference.
In this hands-on session by Deep Tech Stars and Google For Developers, we’ll dive deep into Gemma 4, learn about running models locally, and understand the practical trade-offs between model size, memory, latency and capability. We’ll also look at the evolution of the Gemma family and what the next generation of Gemma models could mean for developers building AI at the edge.
AGENDA
10:30 AM: Welcome note
10:45 AM: Introduction to Gemma series
11:00 AM: Hands-on with Gemma 4 - Code lab on Gemma 4
12:00 PM: Best practices for Gemma 4 deployment
12:30 PM: Usecase brainstorming
1:00 PM: Networking and conclusion
FEE
This workshop is FREE to attend but seats are limited and available on an invite-only basis. Prior registration is required for receiving an invitation, as per the below process.
REGISTRATION
To register, fill in your details in this Luma form by clicking "Request To Join"
If you haven’t done so already, subscribe to the Deep Tech Stars substack, where we explain one new AI concept daily in simple terms and show you how it is used: https://substack.com/@deeptechstars
We thank Google for Developers for co-organizing this session with us. Please reach Nihal at 9663374431 if you need any clarifications or have any challenges in registration.
We look forward to seeing many of you there!