Moonlight-3B/16B

model
Moonshot AI
Lightweight "Pareto-frontier" models trained using the Muon optimizer. Available in 3B and 16B variants.
HuggingFaceGitHubPaper (arXiv)

Model Details

Variants

Name Parameters Notes
Moonlight-3B 3B —
Moonlight-16B 16B —
efficiencyopen-weight