This collection houses Nemotron-3-Super-120B-A12B NIM and Deployment Recipes, which is a large language model (LLM) trained by NVIDIA, designed to deliver strong agentic, reasoning, and conversational capabilities.
Nemotron-3-Super-120B-A12B Overview
Description:
This collection provides the assets needed to deploy Nemotron-3-Super-120B-A12B on Kubernetes as a NIM with Dynamo capabilities: the NIM container, plus validated deployment recipes that stand up a routing frontend in front of multiple GPU worker replicas.
A NIM with Dynamo capabilities keeps the same container, API surface, and operational contract as a standard NIM, and adds KV-aware routing across worker replicas. Requests are directed to the replica that can reuse the most of its existing KV cache, reducing redundant prefill for workloads with shared prefixes such as system prompts, tool definitions, and multi-turn conversations.
Deployments are declared as a single DynamoGraphDeployment custom resource and reconciled by the NVIDIA Dynamo Operator.
License/Terms of Use:
GOVERNING TERMS: The NIM container is governed by the NVIDIA Software License Agreement and the Product-Specific Terms for NVIDIA AI Products.
The use of any models in this container is governed by the NVIDIA Open Model Agreement in addition to any terms which govern the specific models used.
You are responsible for ensuring that your use of any provided models complies with all applicable laws.
The use of this model is governed by the NVIDIA Nemotron Open Model License.
Deployment Geography:
Global
Collection Contents
| Asset | Type | Description |
|---|---|---|
| Nemotron-3-Super-120B-A12B | Container | The NIM. Runs as either the routing frontend or a GPU worker, selected at deploy time. Model details, supported profiles, environment variables, and security scan results are on the container card. |
| Nemotron-3-Super-120B-A12B Deployment Recipes | Resource | DynamoGraphDeployment manifests for supported GPU SKUs and workload types, with prerequisites, secret setup, scaling guidance, and a verification test. |
Deployment Details:
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
Deploying from this collection requires the NVIDIA Dynamo Operator and its CRDs installed on the target cluster. Download the recipe matching your GPU SKU and workload from the Resources section, create the required NGC secrets in your namespace, and apply it with kubectl.
Documentation
Visit the NIM Container LLM page for release documentation, deployment guides, and more.
Security Common Vulnerabilities and Exposures (CVEs)
Please review the Security Scanning tab on the container within this collection to view the latest security scan results. For certain open-source vulnerabilities listed in the scan results, NVIDIA provides a response in the form of a Vulnerability Exploitability eXchange (VEX) document. The VEX information can be reviewed and downloaded from the Security Scanning tab.
Ethical Considerations:
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal teams to ensure these software components meet requirements for the relevant industry and use case and addresses unforeseen product misuse.
Please report quality , risk , security vulnerabilities or NVIDIA AI Concerns here.
Get Help
Getting started with the NIM
Deploying and integrating the NIM is straightforward thanks to our industry standard APIs. Visit the NIM Container page for release documentation, deployment guides and more NIM Container LLM.
Enterprise Support
Get access to knowledge base articles and support cases or submit a ticket.
