AI Model Catalog | Microsoft Foundry Models

Llama 3.3 Nemotron Super 49B v1.5 NIM microservice

Version: 2

Nvidia•Last updated November 2025

Llama-3.3-Nemotron-Super-49B-v1.5 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). It is a reasoning model that is post trained for reasoning, human chat preferences, and agentic tasks, such as 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 ready for commercial use. Llama-3.3-Nemotron-Super-49B-v1.5 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 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.

Intended Use

Primary Use Cases

Llama-3.3-Nemotron-Super-49B-v1.5 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.

By default (empty system prompt) the model will respond in reasoning ON mode. Setting /no_think in the system prompt will enable reasoning OFF mode.
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

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. Prompts have been sourced from either public and open corpus or synthetically generated. Responses were synthetically generated by a variety of models, with some prompts containing responses for both reasoning on and off modes, to train the model to distinguish between two modes. NVIDIA will be releasing the post-training dataset in the coming weeks.

Example Curl Request

#!/bin/bash

curl -X 'POST' \
'<ENDPOINT_URL>/v1/chat/completions' \
    -H 'Accept: application/json' \
    -H 'Content-Type: application/json' \
    -H "Authorization: Bearer <API_KEY>" \
    -d '{
    "messages": [
        {
            "role": "system",
            "content": "/no_think"
        },
        {
            "role": "user",
            "content": "Write a limerick about the wonders of GPU computing."
        }
    ],
    "max_tokens": 256
    }'

We evaluate the model using temperature=0.6, top_p=0.95, and 64k sequence length. We run the benchmarks up to 16 times and average the scores to be more accurate.

MATH500

Reasoning Mode	pass@1 (avg. over 4 runs)
Reasoning On	97.4

AIME 2024

Reasoning Mode	pass@1 (avg. over 16 runs)
Reasoning On	87.5

AIME25

Reasoning Mode	pass@1 (avg. over 16 runs)
Reasoning On	82.71

GPQA

Reasoning Mode	pass@1 (avg. over 4 runs)
Reasoning On	71.97

Source: Llama-3.3-Nemotron-Super-49B-v1.5 Llama-3.3-Nemotron-Super-49B-v1.5 NIM is optimized to run best on the following compute:

GPU	Total GPU memory	Azure VM compute	#GPUs on VM	Link
H100	94	STANDARD_NC40ADS_H100_V5	1	link
H100	188	STANDARD_NC80ADIS_H100_V5	2	link
A100	160	STANDARD_NC48ADS_A100_v4	2	link
A100	320	STANDARD_NC96ADS_A100_V4	4	link

Model Specifications

LicenseCustom

Last UpdatedNovember 2025

Input TypeText

Output TypeText

ProviderNvidia

Languages1 Language

Quick Start