NVIDIA: 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 Ma…
nvidia/nemotron-3-super-120b-a12b-20230311
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.
Specifications & capabilities
- Input
- text
- Output
- text
- Context window · tokens
- 262144
- Published model ID
- NVIDIA-Nemotron-3-Super-120B-A12B-FP8
- Capabilities
- reasoning, structuredOutputs, toolCalling
Description source ↗Evaluations
1–3 / 3
37.7
- source id
- artificialAnalysis
- dimension
- coding
- metric
- Coding Index
Original result ↗12.8
- source id
- artificialAnalysis
- dimension
- intelligence
- metric
- Intelligence Index
Original result ↗1.7
- source id
- artificialAnalysis
- dimension
- agentic
- metric
- Agentic Index
Original result ↗Published prices
1–2 / 2
$0.08
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$0.40
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
Provider specifications & access
1–11 / 11
- source model id
- azure-huggingface/nvidia--nvidia-nemotron-3-super-120b-a12b-fp8@1
- hosting
- foundry-managed-compute
- license
- other
- context length
- 262144
- source model id
- azure-huggingface/nvidia--nvidia-nemotron-3-super-120b-a12b-fp8@2
- hosting
- foundry-managed-compute
- license
- other
- context length
- 262144
- source model id
- azure-huggingface/nvidia--nvidia-nemotron-3-super-120b-a12b-fp8@3
- hosting
- foundry-managed-compute
- license
- other
- context length
- 262144
- source model id
- azure-huggingface/nvidia--nvidia-nemotron-3-super-120b-a12b-fp8@4
- hosting
- foundry-managed-compute
- license
- other
- context length
- 262144
- source model id
- azure-huggingface/nvidia--nvidia-nemotron-3-super-120b-a12b-fp8@5
- hosting
- foundry-managed-compute
- license
- other
- context length
- 262144
- source model id
- azure-huggingface/nvidia--nvidia-nemotron-3-super-120b-a12b-fp8@6
- hosting
- foundry-managed-compute
- license
- other
- context length
- 262144
- source model id
- azure-huggingface/nvidia--nvidia-nemotron-3-super-120b-a12b-fp8@7
- hosting
- foundry-managed-compute
- license
- other
- context length
- 262144
- source model id
- HuggingFace/nvidia-nvidia-nemotron-3-super-120b-a12b-fp8@1
- hosting
- foundry-managed-compute
- license
- nvidia-open-model-license
- source model id
- nvidia/nemotron-3-super-120b-a12b
- hosting
- nvidia-inference-listed
- availability
- Listed by inference API; runtime availability unverified
- source model id
- publishers/hf-nvidia/models/nvidia-nemotron-3-super-120b-a12b-fp8@001
- hosting
- vertex-self-deployed
- source model id
- publishers/nvidia/models/nemotron-v3@nemotron-3-super-120b-a12b-fp8
- hosting
- vertex-self-deployed
Source specification observations
1–9 / 9
- field
- context_length
- value
- 262144
- normalized value
- 262144
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 262144
- normalized value
- 262144
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 262144
- normalized value
- 262144
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 262144
- normalized value
- 262144
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 262144
- normalized value
- 262144
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 262144
- normalized value
- 262144
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 262144
- normalized value
- 262144
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 262144
- normalized value
- 262144
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 16384
- normalized value
- 16384
- scope
- source-model
- source id
- openRouter
- confidence
- 1
Explore more models