InfoQ - Local First - News https://www.infoq.com InfoQ Local First News feed FreeToken Unlocks Frontier MoE Inference on Consumer Hardware via Dynamic Co-Execution https://www.infoq.com/news/2026/08/freetoken-local-inference/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Local+First-news <img src="https://www.infoq.com/styles/static/images/logo/logo_bigger.jpg"/><p>Researchers from UC Berkeley and MIT have developed FreeToken, an open-source inference engine that enhances the utility of Mixture-of-Experts models on consumer hardware. By implementing a dynamic scheduling policy and optimising weight management, FreeToken improves decoding speeds and execution efficiency in edge AI applications, fostering self-hosted reasoning systems.</p> <i>By Olimpiu Pop</i> Local First Large language models Model Inference Frontier Model Local Inference AI, ML & Data Engineering DevOps news Sat, 29 Aug 2026 05:05:00 GMT https://www.infoq.com/news/2026/08/freetoken-local-inference/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Local+First-news Olimpiu Pop 2026-08-29T05:05:00Z /news/2026/08/freetoken-local-inference/en