In this session, Roberto Carratalá and Kevin Dubois tackle the classic “it works on my machine” challenge in the AI era. You’ll discover how to run models locally, test code assistants that plug into those on-premise models, and seamlessly infuse AI smarts into your code without relying on the network.
Along the way, they’ll compare vendors and model sizes to strike the perfect balance of speed versus accuracy, weigh the perks of local versus remote inference, and share practical tips to supercharge your development flow and keep cloud costs—and latency—at bay.
Watch on YouTube
Top comments (0)