# NVIDIA Nemotron 3 Super (free): AI model fact sheet

- **Provider:** nvidia
- **Released:** 2026-03-11
- **Context window:** 262,144 tokens
- **Parameters:** 12B active (120B total)
- **OpenRouter ID:** nvidia/nemotron-3-super-120b-a12b:free
- **Capabilities:** conversation, reasoning, code-generation, analysis, planning, agentic-tool-use

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. Fully open with weights, datasets, and recipes under the NVIDIA Open License.

## Benchmarks

| Benchmark | Score |
| --- | --- |
| AIME 2025 | High |
| SWE-Bench Verified | High |
| TerminalBench | High |

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/nemotron-3-super-120b-a12b-free