This container houses the Llama-3.3-Nemotron-Super-49B-v1.5, which is a significantly upgraded version of Llama-3.3-Nemotron-Super-49B-v1 and is a large language model (LLM) which is a derivative of Meta Llama-3.3-70B-Instruct
Llama-3.3-Nemotron-Super-49B-v1.5 PB6
Description
This container houses the Llama-3.3-Nemotron-Super-49B-v1.5, which is a significantly upgraded version of Llama-3.3-Nemotron-Super-49B-v1 and is a large language model (LLM) which is a derivative of Meta Llama-3.3-70B-Instruct (AKA the reference model).
Llama-3.3-Nemotron-Super-49B-v1.5 is a reasoning model that is post trained for reasoning, human chat preferences, and agentic tasks, such as Retrieval-Augmented Generation (RAG) and tool calling. The model supports a context length of 128K tokens.
Llama-3.3-Nemotron-Super-49B-v1.5 is a model which offers a great tradeoff between model accuracy and efficiency. Efficiency (throughput) directly translates to savings. Using a novel Neural Architecture Search (NAS) approach, we greatly reduce the model’s memory footprint, enabling larger workloads, as well as fitting the model on a single GPU at high workloads (H200). This NAS approach enables the selection of a desired point in the accuracy-efficiency tradeoff. For more information on the NAS approach, please refer to this paper.
The model underwent a multi-phase post-training process to enhance both its reasoning and non-reasoning capabilities. This includes a supervised fine-tuning stage for Math, Code, Science, and Tool Calling. Additionally, the model went through multiple stages of Reinforcement Learning (RL) including Reward-aware Preference Optimization (RPO) for chat, Reinforcement Learning with Verifiable Rewards (RLVR) for reasoning, and iterative Direct Preference Optimization (DPO) for Tool Calling capability enhancements. The final checkpoint was achieved after merging several RL and DPO checkpoints.
This model is part of the Llama Nemotron Collection. You can find the other model(s) in this family here:
The Llama-3.3-Nemotron-Super-49B-v1.5 NIM Production Branch, exclusively available with NVIDIA AI Enterprise, is a 9-month supported, API-stable branch that includes monthly fixes for high and critical software vulnerabilities. This branch provides a stable and secure environment for building your mission-critical AI applications. The Llama-3.3-Nemotron-Super-49B-v1.5 NIM production branch releases every six months with a three-month overlap in between two releases.
The container components are ready for commercial/non-commercial use.
Documentation
Visit the NIM Container LLM page for release documentation, deployment guides, and more.
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.
Use of this model is governed by the NVIDIA Open Model Agreement. The underlying model is also licensed under the Llama 3.3 Community License Agreement. Built with Llama.
Deployment Geography
Global
Release Date:
- Hugging Face 7/25/2025 via Llama-3_3-Nemotron-Super-49B-v1_5
- build.nvidia.com 7/25/2025 Llama-3_3-Nemotron-Super-49B-v1_5
Program Classes:
Llama-3.3-Nemotron-Super-49B-v1.5 Container includes the following model:
| Model Name & Link | Use Case | How to Pull the Model |
|---|---|---|
| Llama-3.3-Nemotron-Super-49B-v1.5 | This is a large language model (LLM) that is a derivative of the Meta Llama-3.3-70B-Instruct. It is a reasoning model that is post-trained for reasoning, human chat preferences, and agentic tasks, such as RAG and tool calling. | Automatic |
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.
Security Common Vulnerabilities and Exposures (CVEs)
Please review the Security Scanning tab on NGC 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 developer team to ensure these software components meet requirements for the relevant industry and use case and address unforeseen product misuse.
Please report quality, risk, security vulnerabilities or NVIDIA AI Concerns here.
Get Help
Enterprise Support
Get access to knowledge base articles and support cases or submit a ticket. You are responsible for ensuring that your use of NVIDIA provided models complies with all applicable laws.