Gemma 4 E2B running in-browser at 255 tok/s

A new Hugging Face Space demonstrates Gemma 4 E2B running in-browser via WebGPU at 255 tokens per second, showcasing efficient on-device AI inference.

Article URL: https://huggingface.co/spaces/webml-community/gemma-4-webgpu-kernels Comments URL: https://news.ycombinator.com/item?id=48577195 Points: 3 Comments: 0