Saturday, October 24, 2026 · 10:00 am – 1:00 pm
Price
Free
What it is A hands-on, invite-only workshop in Mumbai dedicated to on-device AI with Gemma 4, the latest model in Google's open Gemma family. The session is organised by Deep Tech Stars, an AI-focused community that publishes a daily Substack explaining one new AI concept in simple terms, and is co-organised with Google for Developers.
Why it matters The Gemma family crossed 1 billion downloads in August 2026, and Gemma 4 is built to run locally on phones, laptops and other edge devices. That shift brings lower latency, greater privacy, reduced inference costs, and independence from cloud inference - a combination that matters a great deal to Indian product teams building consumer and enterprise AI where data residency, cost per query and offline reliability are real constraints.
Who it's for Developers, ML engineers, product builders and technical founders who want to move beyond API calls and actually ship models on-device. The format assumes you can code; the code lab is practical rather than conceptual.
Agenda
What you'll take away A working understanding of running models locally, plus the practical trade-offs between model size, memory, latency and capability - the decisions that determine whether an on-device feature is viable in production. The session also covers what the next generation of Gemma models could mean for developers building AI at the edge.
Registration and fee The workshop is free to attend, but seats are limited and entry is invite-only. Prior registration is required: submit your details via the Luma form using "Request To Join", and subscribe to the Deep Tech Stars Substack. Invitations are issued on that basis. For clarifications or registration issues, contact Nihal at 9663374431.
Price
Free