Moonlight 16B A3B Instruct
Moonshot AI's Moonlight 16B A 3B Instruct is a chat model that excels at handling large contexts with its 8,192 token context window. It is notably trained using the Muon optimizer with techniques such as weight decay and consistent RMS updates, allowing for efficient scaling to large models.
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 Instruct
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.