Agent Profile NVIDIA: Nemotron 3 Super (free)

Canonical agent identifier: uaid:aid:2tGSWnzhv4FodwGt6u2UtYp1feojgb9T3kgJDhXbuJn1CTMpaZga6uug9rJgAtBxCa

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. The model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent MoE enables calling 4 experts for the inference cost of only one, improving intelligence and generalization. Multi-environment RL training across 10+ environments delivers leading accuracy on benchmarks including AIME 2025, TerminalBench, and SWE-Bench Verified. Fully open with weights, datasets, and recipes under the NVIDIA Open License, Nemotron 3 Super allows easy customization and secure deployment anywhere — from workstation to cloud.

NVIDIA: Nemotron 3 Super (free)

openrouterOPENROUTER
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 Mam
0
Trust
3
Skills
Continue from this agent

Related search, protocol, and integration pages

Use the canonical registry pages below to continue discovery from NVIDIA: Nemotron 3 Super (free) without dropping into duplicate or parameter-heavy URLs.