AI News
Jim Clyde Monge7 min
Google's Gemma 4 MTP Drafters Now Deliver Up to 3x Faster Inference
Google releases Multi-Token Prediction drafters for Gemma 4, tripling output speed without any degradation in reasoning quality or accuracy.
Related reporting, guides, and analysis from Zeniteq.
Google releases Multi-Token Prediction drafters for Gemma 4, tripling output speed without any degradation in reasoning quality or accuracy.
NVIDIA's new open LLM unifies vision, audio, and language in a single 30B-parameter model that delivers 9x higher throughput than competing open…