i spent the afternoon experimenting with Gemma 4's vision...

made an app that uses roboflow RF-DETR for a first pass of object detections and Gemma to summarize the scene in one sentence
for fun i asked Gemma to "describe what you see as if you were a medieval bard"
all made with free local AI models (running via webgpu in the browser thanks to transformers js)
lots more possibilities to explore with this
x.com/GoogleDeepMind…
models: RF-DETR and Gemma-4-E2B