FreeToken Unlocks Frontier MoE Inference on Consumer Hardware via Dynamic Co-Execution

2026-08-28 20:05 GMT · 11 hours ago aimagpro.com

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. By Olimpiu Pop