Nemotron 3 Super
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models.
Input
Output
Context
262K
Max Output
—
Parameters
120B
Technical Specifications
Model TypeChat
Context Window262K
Max Output Tokens—
Parameters120B
Training Cutoff—
License—
Capabilities
Input Modalities
text
Output Modalities
text
Features
function_callingjson_modestreamingtext_generation
Resources & Links
Estimated GPU Requirements for Nemotron 3 Super
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: May 5, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.