Reported evidence
Muon → compares → AdamW
Moonshot AI reports approximately twice AdamW’s compute efficiency for the complete Muon design under compute-optimal training conditions. The result neither isolates the contributions of individual modifications nor establishes the same gains across other models, hardware, and configurations.
Read the evidence
The project team states that these adjustments improved training stability; in scaling experiments using the complete approach under compute-optimal training conditions, Muon’s compute efficiency was approximately twice that of AdamW.Read the full research