Llama 3.3 Nemotron Super 49B v1 NIM microservice
Version: 2
Llama-3.3-Nemotron-Super-49B-v1 is a large language model (LLM) which is a derivative of Meta Llama-3.3-70B-Instruct (AKA the reference model). It is a reasoning model that is post trained for reasoning, human chat preferences, and tasks, such as RAG and tool calling. The model supports a context length of 128K tokens.
Llama-3.3-Nemotron-Super-49B-v1 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.
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, Reasoning, and Tool Calling as well as multiple reinforcement learning (RL) stages using REINFORCE (RLOO) and Online Reward-aware Preference Optimization (RPO) algorithms for both chat and instruction-following. The final model checkpoint is obtained after merging the final SFT and Online RPO checkpoints. For more details on how the model was trained, please see this blog .
Llama-3.3-Nemotron-Super-49B-v1 is available as an NVIDIA NIM™ microservice, part of NVIDIA AI Enterprise . NVIDIA NIM offers prebuilt containers for large language models (LLMs) that can be used to develop chatbots, content analyzers—or any application that needs to understand and generate human language. Each NIM consists of a container and a model and uses a CUDA-accelerated runtime for all NVIDIA GPUs, with special optimizations available for many configurations. NVIDIA NIM is the fastest way to achieve accelerated generative AI inference at scale and has been benchmarked to have up to 2.6x improved throughput latency.
NVIDIA AI Enterprise
NVIDIA AI Enterprise is an end-to-end, cloud-native software platform that accelerates data science pipelines and streamlines development and deployment of production-grade co-pilots and other generative AI applications. Easy-to-use microservices provide optimized model performance with enterprise-grade security, support, and stability to ensure a smooth transition from prototype to production for enterprises that run their businesses on AI.
NVIDIA AI Enterprise is an end-to-end, cloud-native software platform that accelerates data science pipelines and streamlines development and deployment of production-grade co-pilots and other generative AI applications. Easy-to-use microservices provide optimized model performance with enterprise-grade security, support, and stability to ensure a smooth transition from prototype to production for enterprises that run their businesses on AI.
Intended Use
Primary Use Cases
Llama-3.3-Nemotron-Super-49B-v1 is a general purpose reasoning and chat model intended to be used in English and coding languages. Other non-English languages (German, French, Italian, Portuguese, Hindi, Spanish, and Thai) are also supported.- Reasoning mode (ON/OFF) is controlled via the system prompt, which must be set as shown in the example below.
- All instructions should be contained within the user prompt
- We recommend setting temperature to 0.6, and Top P to 0.95 for Reasoning ON mode
- We recommend using greedy decoding for Reasoning OFF mode
- We have provided a list of prompts to use for evaluation for each benchmark where a specific template is required
Responsible AI 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 model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.Training Data
A large variety of training data was used for the knowledge distillation phase before post-training pipeline, 3 of which included: FineWeb, Buzz-V1.2, and Dolma. The data for the multi-stage post-training phases for improvements in Code, Math, and Reasoning is a compilation of SFT and RL data that supports improvements of math, code, general reasoning, and instruction following capabilities of the original Llama instruct model. In conjunction with this model release, NVIDIA has released 30M samples of post-training data, as public and permissive. Llama-Nemotron-Post-Training-Dataset-v1| Category | Value |
|---|---|
| math | 19,840,970 |
| code | 9,612,677 |
| science | 708,920 |
| instruction following | 56,339 |
| chat | 39,792 |
| safety | 31,426 |
- Llama-3.3-70B-Instruct
- Llama-3.1-Nemotron-70B-Instruct
- Llama-3.3-Nemotron-70B-Feedback/Edit/Select
- Mixtral-8x22B-Instruct-v0.1
- DeepSeek-R1
- Qwen-2.5-Math-7B-Instruct
- Qwen-2.5-Coder-32B-Instruct
- Qwen-2.5-72B-Instruct
- Qwen-2.5-32B-Instruct
These results contain both Reasoning On, and Reasoning Off. We recommend using temperature=0.6, top_p=0.95 for Reasoning On mode, and greedy decoding for Reasoning Off mode. All evaluations are done with 32k sequence length. We run the benchmarks up to 16 times and average the scores to be more accurate.
NOTE: Where applicable, a Prompt Template will be provided. While completing benchmarks, please ensure that you are parsing for the correct output format as per the provided prompt in order to reproduce the benchmarks seen below.
Source: Llama-3.3-Nemotron-Super-49B-v1
Llama-3.3-Nemotron-Super-49B-v1 NIM is optimized to run best on the following compute:
Arena-Hard
| Reasoning Mode | Score |
|---|---|
| Reasoning Off | 88.3 |
MATH500
| Reasoning Mode | pass@1 |
|---|---|
| Reasoning Off | 74.0 |
| Reasoning On | 96.6 |
AIME25
| Reasoning Mode | pass@1 |
|---|---|
| Reasoning Off | 13.33 |
| Reasoning On | 58.4 |
GPQA
| Reasoning Mode | pass@1 |
|---|---|
| Reasoning Off | 50 |
| Reasoning On | 66.67 |
| GPU | Total GPU memory | Azure VM compute | #GPUs on VM | Link |
|---|---|---|---|---|
| A100 | 320 | Standard_NC96ads_A100_v4 | 4 | link |
| A100 | 640 | STANDARD_ND96AMSR_A100_V4 | 8 | link |
| H100 | 188 | STANDARD_NC80ADIS_H100_V5 | 2 | link |
Model Specifications
LicenseCustom
Last UpdatedMay 2025
Input TypeText
Output TypeText
PublisherNvidia