§ feed · storyline
FreeToken runs 753B GLM-5.2 on single GPU
FreeToken launches an edge-native MoE serving engine that runs the 753B GLM-5.2 model on a single workstation GPU via adaptive hardware computation mapping.
FreeToken is a new edge-native MoE serving engine designed to run massive models like GLM-5.2 on a single workstation GPU by mapping computation to available hardware.
§ sources1 publication · timeline below