Multi-token-prediction in Gemma 4

kept by eddie may 06

Google released Multi-Token Prediction drafters for Gemma 4 that use speculative decoding to achieve up to 3x faster inference without output quality loss.

Google's new Gemma 4 12B model is designed to run on any laptop with 16GB of RAM - Ars Technica
Google's Gemma 4 12B model uses Multi-Token Prediction and a streamlined multimodal encoder to run efficiently on laptops with 16GB RAM, matching larger models.
also on Gemma 4, #machine-learning, Google, #open-source, #ai, #developer-tools
Gemma 4 WebGPU Kernels - a Hugging Face Space by webml-community
Gemma 4 E2B runs locally in-browser via WebGPU, letting users prompt the model directly without server-side inference.
also on Gemma 4, #machine-learning, #open-source, #ai