Gemini's live video mode is my faborite LLM model and i got inspired by @measure_plan after the release of Gemma.
My 16gb macbook Pro m1 was acting as a server while I played with the e2b model on mobile, the capabilities are insane.
i spent the afternoon experimenting with Gemma 4's vision capabilities
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