NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16

Model Overview

Model Developer: NVIDIA Corporation

Model Dates:

December 2025 - April 2026

Data Freshness:

• The pre-training data has a cutoff date of September 2025.

Description

NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16 is a large language model (LLM) trained by NVIDIA.

The model employs a hybrid Latent Mixture-of-Experts (LatentMoE) architecture, utilizing interleaved Mamba-2 and MoE layers, along with select Attention layers. Distinct from the Nano model, the Ultra model incorporates Multi-Token Prediction (MTP) layers for faster text generation and improved quality, and it is pre-trained using an NVFP4 recipe to maximize compute efficiency. The model has 55B active parameters and 550B parameters in total.

The supported languages include: English, French, Spanish, Italian, German, Japanese, Hindi, Korean, Brazilian Portuguese, and Chinese.

This model is ready for commercial and non-commercial use.

What is Nemotron?

NVIDIA Nemotron™ is a family of open models with open weights, training data, and recipes, delivering leading efficiency and accuracy for building specialized AI agents.

License/Terms of Use

Use of this model is governed by the OpenMDW License Agreement, version 1.1 (OpenMDW-1.1).

Benchmarks

Comparison of Nemotron-3-Ultra-550B-A55B-Base, DeepSeek-V3.2-Exp-Base, Mistral-Large-3-675B-Base-2512, Kimi-K2-Base, and GLM-4.5-Base. Best available results are marked in bold.

All evaluation results were collected via Nemo Evaluator SDK and NVIDIA's open source container of LM Evaluation Harness, unless otherwise stated. For reproducibility purposes, more details on the evaluation settings can be found in the Nemo Evaluator SDK examples folder and the reproducibility tutorial for Nemotron 3 Ultra. The open source container on LM Evaluation Harness packaged via NVIDIA's Nemo Evaluator SDK used for evaluations can be found here.

Deployment Geography: Global

Use Case

This model is intended for developers and researchers building LLMs.

Release Date

Hugging Face - 06/04/2026 via Hugging Face

Reference(s)

• NVIDIA Nemotron 3 model family on Hugging Face
• NVIDIA Nemotron 3 Ultra Technical Report

Model Architecture

• Architecture Type: Mamba2-Transformer Hybrid Latent Mixture of Experts (LatentMoE) with Multi-Token Prediction (MTP)
• Network Architecture: Nemotron Hybrid LatentMoE
• Number of model parameters: 550B Total / 55B Active

Model Design

The model was pre-trained with around 20T tokens and supports up to 1M context length. The pre-training phase used an NVFP4 recipe. It utilizes the LatentMoE architecture, where tokens are projected into a smaller latent dimension for expert routing and computation, improving accuracy per byte. The model includes Multi-Token Prediction (MTP) layers, which predict multiple future tokens to provide richer training signals and enable faster inference via speculative decoding.

Training Methodology

Stage 1: Pre-Training

• NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16 model was pre-trained using an NVFP4 recipe with crawled and synthetic code, math, science, and general knowledge data.

• Software used for pre-training: Megatron-LM

NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16 model is a result of the above work.

Input

• Input Type(s): Text
• Input Format(s): String
• Input Parameters: One-Dimensional (1D): Sequences
• Other Properties Related to Input: Maximum context length up to 1M tokens. Supported languages include: English, French, Spanish, Italian, German, Japanese, Korean, Hindi, Korean, Brazilian Portuguese, and Chinese

Output

• Output Type(s): Text
• Output Format: String
• Output Parameters: One-Dimensional (1D): Sequences
• Other Properties Related to Output: Maximum context length up to 1M tokens

Our AI models are designed and 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.

Software Integration

• Runtime Engine(s): NeMo 26.04.01
• Supported Hardware Microarchitecture Compatibility: NVIDIA Ampere - A100; NVIDIA Blackwell; NVIDIA Hopper - H100-80GB
• Operating System(s): Linux

The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.

Model Version(s)

• v1.0 - GA

Training and Evaluation Datasets:

Training

Data Modality: Text

The total size: 53.8 TiB (14.8 trillion tokens)

Total number of datasets: 131

Dataset partition: Training [100%], testing [0%], validation [0%]

Time period for training data collection: 2013 to 2025

Time period for testing data collection: 2013 to 2025

Time period for validation data collection: 2013 to 2025

Data Collection Method by dataset: Hybrid: Automated, Human, Synthetic

Labeling Method by dataset: Hybrid: Automated, Human, Synthetic

Properties: NVIDIA-Nemotron-3-Ultra-550B-A55B-Base is pre-trained on a large corpus of high-quality curated and synthetically-generated data. It is trained in the English language, as well as 11 other languages and 43 programming languages. Our sources cover a variety of document types such as: webpages, dialogue, articles, and other written materials. The corpus spans domains including legal, math, science, finance, and more. We also include a small portion of question-answering, and alignment style data to improve model accuracy. The model was trained for approximately 20T tokens.

More details on the datasets and synthetic data generation methods can be found in the technical report NVIDIA Nemotron 3 Ultra.

For more information about the datasets used to train this model, please see the Public Summary of Training Content

Base Pre-Training Corpus (Nemotron 3 Foundation)

The foundation of the model is trained on the Nemotron-3-Ultra corpus, comprising the following datasets from the Nemotron Pre-Training Datasets collection:

Public Datasets

Crawled and Scraped from Online Sources by NVIDIA

The English Common Crawl data was downloaded from the Common Crawl Foundation (see their FAQ for details on their crawling) and includes the snapshots CC-MAIN-2013-20 through CC-MAIN-2025-13. The data was subsequently deduplicated and filtered in various ways described in the Nemotron-CC paper. Additionally, we extracted data for fifteen languages from the following three Common Crawl snapshots: CC-MAIN-2024-51, CC-MAIN-2025-08, CC-MAIN-2025-18. The fifteen languages included were Arabic, Chinese, Danish, Dutch, French, German, Italian, Japanese, Korean, Polish, Portuguese, Russian, Spanish, Swedish, and Thai. As we did not have reliable multilingual model-based quality classifiers available, we applied just heuristic filtering instead—similar to what we did for lower quality English data in the Nemotron-CC pipeline, but selectively removing some filters for some languages that did not work well. Deduplication was done in the same way as for Nemotron-CC.

The GitHub Crawl was collected using the GitHub REST API and the Amazon S3 API. Each crawl was operated in accordance with the rate limits set by its respective source, either GitHub or S3. We collect raw source code and subsequently remove any having a license which does not exist in our permissive-license set (for additional details, refer to the technical report).

Private Non-publicly Accessible Datasets of Third Parties

Private Non-publicly Accessible Datasets by NVIDIA

NVIDIA-Sourced Synthetic Datasets

Testing Datasets:

Data Collection Method by dataset

• Hybrid: Automated, Human, Synthetic

Labeling Method by dataset

• Hybrid: Automated, Human, Synthetic

Properties: This corpus comprises a mix of high-quality standard benchmarks and test suites for modern agentic AI as outlined in the benchmark section of the model card.

Evaluation Datasets:

Data Collection Method by dataset

• Hybrid: Automated, Human, Synthetic

Labeling Method by dataset

• Hybrid: Automated, Human, Synthetic

Properties: This corpus comprises a mix of high-quality standard benchmarks and test suites for modern agentic AI as outlined in the benchmark section of the model card.

Inference

• Test Hardware:
  • NVIDIA Hopper
    • H100
    • H200
  • NVIDIA Grace Blackwell
    • GB200
    • GB300
  • NVIDIA Blackwell
    • B200
    • B300

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 model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.

We advise against circumvention of any provided safety guardrails contained in the Model without a substantially similar guardrail appropriate for your use case. For more details: Safety and Explainability subcards.For more detailed information on ethical considerations for this model, please see the Model Card++ Bias, and Privacy subcards.

Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns here.

Citation

@misc{nvidia_nemotron_3_ultra_2026,
  title  = {Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning},
  author = {{NVIDIA}},
  year   = {2026},
  url    = {https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3-Ultra-Technical-Report.pdf},
  note   = {White Paper}
}