Your First Steps into Local Models

With the latest release of Gemma 4, local models have once again gained traction. The barriers to entry have never been lower, and the performance on consumer hardware has never been higher.

This session is designed for builders who want to stop relying solely on cloud APIs and start exploring the world of private, offline, and cost-effective AI.

Curriculum (60 Minutes)

• Session Intro (5 min): The shift back to local—why privacy and latency are winning.
• Introduction to Ollama & Local Setup (20 min): Installing the stack and pulling your first models without the headache.
• Getting Started with Gemma 4 (20 min): Why Gemma 4 is game-changing for local reasoning and how to prompt it effectively.
• Closing Q&A (15 min): Hardware recommendations, production use cases, and next steps.

What you will learn

• How to run state-of-the-art models securely on your own machine.
• The workflow for using Ollama as a local inference engine.
• Leveraging the unique performance characteristics of the Gemma 4 architecture.

Format

• 1-hour live session
• Host: Rodrigo Rivera
• Interactive demo and real-time setup

Who should join

Developers and Product Engineers who want a "zero-to-one" guide to the local AI ecosystem. No previous experience with local LLMs is required.