Moonlight 16B A3B
Moonshot AI's Moonlight 16B A 3B is a chat model that excels at handling large contexts with its 8,192 token context window, making it well-suited for complex and lengthy conversations. It is trained using the Muon optimizer, which has been scaled up to work efficiently with large models through techniques such as weight decay and consistent RMS updates.
Input
Output
Context
8K
Max Output
-
Parameters
16B
Technical Specifications
Model TypeChat
Context Window8,192 tokens
Max Output TokensNot available
Parameters16B
Release DateFeb 22, 2025
Training CutoffJun 1, 2024
Licensemit
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Estimated GPU Requirements for Moonlight 16B A3B
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.