Moonlight 16B
ModelMoonshot AIresearch
Open 16B-parameter mixture-of-experts model used to study Muon optimization at scale.
- —
- —
- —
- Yes
- —
- 1
Releases
Feb 2025Moonlight 16B research weights releasedOpen weights
Moonshot released Moonlight, a 16B MoE model used to evaluate Muon optimization at scale.

