InfoQ - Mobile - News https://www.infoq.com InfoQ Mobile News feed Google LiteRT-LM Speeds Up Local Inference Up to 2.2x With Gemma 4 Multi-Token Prediction https://www.infoq.com/news/2026/06/google-litertlm-gemma4/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Mobile-news <img src="https://res.infoq.com/news/2026/06/google-litertlm-gemma4/en/headerimage/google-litert-ml-gemma4-1780649451174.jpeg"/><p>LiteRT-LM brings native support for Gemma 4 Multi-Token Prediction (MTP) drafters, enabling up to 2.2x faster inference. The framework is expanding beyond Kotlin and C++ adding support for new Swift and a JavaScript APIs.</p> <i>By Sergio De Simone</i> TensorFlow Large language models Google Gemma Edge Computing Mobile Agents AI, ML & Data Engineering Development news Fri, 05 Jun 2026 09:00:00 GMT https://www.infoq.com/news/2026/06/google-litertlm-gemma4/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Mobile-news Sergio De Simone 2026-06-05T09:00:00Z /news/2026/06/google-litertlm-gemma4/en