Google's Gemma 4 is a family of open AI models that can run locally on your own hardware for free, with no data sent to the cloud. It comes in four sizes (E2B, E4B, 26B, 31B) suited for different hardware configurations, with the default model running on 8GB RAM. The tutorial covers trying Gemma 4 in Google AI Studio without installation, then installing Ollama to run it locally. Capabilities demonstrated include text generation, image understanding, code generation, and reasoning tasks. The E4B model is recommended for most users as a starting point.

12m watch time

Sort: