Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Watch this 18-minute live demo from the Gemma3 launch event at Google Paris, where Asier Arranz, Senior Developer Advocate at NVIDIA, showcases Gemma3 4B running smoothly on Jetson Nano at 15 tokens per second. Discover how this lightweight edge hardware can handle powerful Visual Language Models, including a surprising demonstration of the larger Gemma3 12B model on the same tiny device. Perfect for developers and enthusiasts interested in deploying advanced AI models at the edge. The presentation provides practical examples and real-world applications of running these models on resource-constrained hardware.
