Nvidia Brings Google’s Gemma 4 to PCs and Edge Devices as AI Moves Beyond the Cloud
Nvidia announced it has optimized Google’s new Gemma 4 AI models to run on its RTX PCs, DGX Spark systems, and Jetson modules. Google said Gemma 4, released under an Apache 2.0 license, includes four model sizes and supports over 140 languages, with larger versions able to run on a single Nvidia H100 GPU. Nvidia’s data-center sales reached $62.3 billion last quarter. Competitors are increasing efforts in AI inference chips.