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

August 29, 2026 · 5:05 am 1 sources

Coverage

More coverage

• FreeToken Unlocks Frontier MoE Inference on Consumer Hardware via Dynamic Co-Execution
  InfoQ · August 29, 2026 05:05
  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…