Model release

NVIDIA Nemotron 3 Ultra 550B-A55B

NVIDIA Nemotron 3 Ultra 550B-A55B is an open-weight model release in the NVIDIA Nemotron family from NVIDIA1, version 3 Ultra (550B-A55B), v1.0, released Jun 4, 2026. Its weights can be downloaded by the public1 2 under the OpenMDW License Agreement, version 1.11 3.

Nemotron 3 Ultra is an NVIDIA language model with 550B total and 55B active parameters, built on a hybrid Mamba-2 and attention architecture with latent mixture-of-experts layers and multi-token prediction. Reasoning can be switched on or off through the chat template. NVIDIA released BF16 and NVFP4 checkpoints and a separate base checkpoint on Hugging Face.1

Model hub: Model card (BF16) (external site: huggingface.co)
License: OpenMDW License Agreement, version 1.1 (external site: raw.githubusercontent.com)
Documentation: Nemotron 3 Ultra training recipe (external site: github.com)

On AI on Hugging Face: nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16

Last reviewedSep 29, 2026Entry updated Oct 2, 2026Documented release Jun 4, 2026

Availability and license

Overall availability

Public

Weights are downloadable from Hugging Face under the OpenMDW-1.1 license; the repository metadata showed no access gate when checked.1 2

Availability fact review: not separately recorded

Availability is separate from permission: read the license before using or redistributing.

OpenMDW License Agreement, version 1.1 (external site: raw.githubusercontent.com)1 3
Applies to: Weights · custom license (no SPDX identifier) · fact-level rights review not recorded
Plain-language guide to the OpenMDW License Agreement, version 1.1
Apache License 2.0 (Nemotron Developer Repository training recipes) (external site: raw.githubusercontent.com)5
Applies to: Code · SPDX Apache-2.0 · on the rubric’s OSI-approved software-license list · fact-level rights review not recorded
Plain-language guide to the Apache License 2.0

OpenMDW-1.1 grants free permission to use, modify, and share the model materials without restriction, including under copyright, patent, database, and trade secret rights. Redistributors must include a copy of the agreement and keep applicable origin notices. All rights end for anyone who sues claiming the materials infringe a patent or copyright, unless responding to a suit brought against them first. It imposes no conditions on outputs, disclaims warranties, and leaves clearing third-party rights to the user. The SPDX list (version 3.29.0) includes OpenMDW-1.0 but not version 1.1, so no SPDX ID is recorded.3 4

Component reuse rights

A readable or downloadable component is not automatically reusable. These indicators concern recorded license evidence, not system certification.

weights: Unknown — no complete fact-level rights review
code: Unknown — no complete fact-level rights review
data: Unknown — no complete fact-level rights review
documentation: Unknown — no complete fact-level rights review

No complete system-rights review is recorded for this release.

Model-disclosure tier

Computed from the checklist below using USASI rubric v0.2. An editorial category, not a certification.

Open-weight

The model parameters for this release can be downloaded by the public. License terms may still restrict use, redistribution, or commercial use.

The weights are under a license that is not on the rubric's OSI-approved list. Read its terms before use.

How tiers are computed

Public materials checklist

Items for a model under USASI rubric v0.2. Unknown means unassessed or insufficient evidence.

Public materials checklist for NVIDIA Nemotron 3 Ultra 550B-A55B
Item	Status	Notes and evidence
WeightsCan the general public download the model parameters for this release?	Public	BF16 and NVFP4 post-trained checkpoints and a BF16 base checkpoint are published on Hugging Face.1 2
Inference codeIs code for running the model published?	Public	The model card gives deployment instructions for vLLM, SGLang, and TensorRT-LLM.1
Training codeIs the code used to train the model published?	Public	The Apache-2.0 Nemotron Developer Repository provides pretraining and SFT recipes built on Megatron-Bridge and a representative RL/distillation pass using NeMo RL.6 5
Training-data informationDoes the information cover provenance, scope, acquisition, selection, labeling, processing, and where data or alternatives can be obtained? Access alone does not establish completeness.	Unknown	Not assessed.
Training-data accessCan the training data be obtained? This is independent of information completeness and reuse rights; original unshareable data need not be downloadable.	Partial	The model card says NVIDIA releases its final pre-training and post-training data, with an ungated sample set and gating and approval required for the remaining code, math, and multilingual data. It also lists third-party and NVIDIA datasets used in training as private and not publicly accessible. NVIDIA's training recipe adds that the data for the 1M-token long-context phase is not open source.1 6
Complete training pipelineIs the complete base-training and preprocessing pipeline published, including configuration? Fine-tuning code or an inference SDK alone is insufficient.	Unknown	Not assessed.
Legacy data assessment (v0.1)Historical assessment combining download access and disclosure. Preserved for traceability; excluded from the v0.2 tier calculation. See the new separate assessments above.	Partial	The model card lists the pre- and post-training datasets. Major portions are released in Hugging Face collections, some requiring access approval, while several third-party and NVIDIA datasets are listed as private and not publicly accessible.1 7
Training recipeAre the training configuration and procedure documented in enough detail to follow?	Partial	NVIDIA's recipe covers pretraining and SFT, but states that the full multi-iteration RL and on-policy distillation pipeline is not reproduced because the intermediate teacher checkpoints it depends on have not been released. It also omits the 1M-token long-context pretraining phase because that data is not open-source.6
Evaluation materialsPublic = evaluation code or prompts that let others re-run the evaluations are published. Partial = results only.	Public	The model card publishes benchmark results and points to the NeMo Evaluator SDK for replication; it says some benchmarks used internal scaffolding not yet open-sourced.1

What it is useful for

The model card lists agentic workflows, long-context analysis, tool use, multilingual reasoning, and retrieval-augmented generation, and states the model is ready for commercial and non-commercial use.1

Run and use notes

Documented facts only. No hardware or performance claims are made without a cited source and stated assumptions.

The model card documents serving with vLLM, SGLang, and TensorRT-LLM, and lists NVIDIA Hopper (H100, H200), Grace Blackwell (GB200, GB300), and Blackwell (B200, B300) GPUs as test hardware.1
For the BF16 checkpoint, the model card states a minimum of 8x GB200/B200/GB300/B300, 16x H100, or 8x H200 GPUs, and points to the separate NVFP4 checkpoint for a smaller footprint.1

Organization context

NVIDIA

Provenance and derivatives

Post-trained by NVIDIA (supervised fine-tuning, reinforcement learning, and multi-domain on-policy distillation) from its own pre-trained Nemotron 3 Ultra base checkpoint. The model card says post-training synthetic data was generated with teacher models, including third-party open models such as GPT-OSS-120B.1

Derived from: NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16 (external site: huggingface.co) — NVIDIA's pre-trained base checkpoint for this release.

Other releases in the NVIDIA Nemotron family

NVIDIA Nemotron 3 Super 120B-A12BModel-disclosure tier (USASI rubric v0.2): Open-weight
NVIDIA Nemotron 3.5 Lightning 30B-A3BModel-disclosure tier (USASI rubric v0.2): Open-weight
NVIDIA Nemotron 3.5 Super VL 120B-A12BModel-disclosure tier (USASI rubric v0.2): Open-weight
NVIDIA Nemotron Labs Dory1.0-4BModel-disclosure tier (USASI rubric v0.2): Open-weight

NVIDIA Nemotron family overview

What this catalog does not know

Unknown means the sources reviewed for this record do not document it. It is not evidence that something does not exist.

Training-data information: unknown.
Complete training pipeline: unknown.

Have a primary source? How to report a correction.

U.S. eligibility

Project eligibility rests on documented governing or maintaining entities, not on contributors.

Eligible · basis: U.S. headquarters

The model card names NVIDIA Corporation as the model developer. NVIDIA's principal executive offices are in Santa Clara, California, per its Form 10-Q for the quarter ended July 26, 2026.1 8

Assessed Sep 29, 2026

Sources

1.
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 model card (external site: huggingface.co)
NVIDIA (Hugging Face) · Model card · published Jun 4, 2026 · accessed Oct 2, 2026
2.
Hugging Face model metadata for nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 (external site: huggingface.co)
Hugging Face · Other · accessed Sep 29, 2026
3.
OpenMDW License Agreement, version 1.1 (OpenMDW-1.1) (external site: raw.githubusercontent.com)
OpenMDW (GitHub) · License · accessed Sep 29, 2026
4.
SPDX License List data (licenses.json, version 3.29.0) (external site: raw.githubusercontent.com)
SPDX · Other · published Sep 16, 2026 · accessed Sep 29, 2026
5.
NVIDIA Nemotron Developer Repository LICENSE (Apache License 2.0) (external site: raw.githubusercontent.com)
NVIDIA (GitHub) · License · accessed Sep 29, 2026
6.
Nemotron 3 Ultra Training Recipe (external site: raw.githubusercontent.com)
NVIDIA (GitHub) · Documentation · accessed Oct 2, 2026
7.
Nemotron-Pre-Training-Datasets collection (external site: huggingface.co)
NVIDIA (Hugging Face) · Dataset card · accessed Sep 29, 2026
8.
NVIDIA Corporation Form 10-Q for the quarter ended July 26, 2026 (external site: sec.gov)
U.S. Securities and Exchange Commission (EDGAR) · Filing · published Aug 26, 2026 · accessed Sep 29, 2026

Email a correction Report a correction Edit this entry

This listing is not an endorsement, a safety assessment, or a federal approval.

Cite this page

APA style

USASI. (2026, October 2). NVIDIA Nemotron 3 Ultra 550B-A55B. United States of America Superintelligence. https://unitedstatesofamericasuperintelligence.com/open/nemotron-3-ultra-550b-a55b/

BibTeX

@misc{usasi_nemotron_3_ultra_550b_a55b,
  author = {{USASI}},
  title = {NVIDIA Nemotron 3 Ultra 550B-A55B},
  year = {2026},
  month = oct,
  howpublished = {\url{https://unitedstatesofamericasuperintelligence.com/open/nemotron-3-ultra-550b-a55b/}},
  note = {United States of America Superintelligence. Last updated 2026-10-02}
}

The date is when this page was last updated. Add the date you read it if your style needs one.

For maintainers: a “Listed in USASI” badge

Links to this page. It says the entry is listed, not endorsed or rated. About the badge

Markdown (for a README)

[![Listed in the USASI catalog](https://unitedstatesofamericasuperintelligence.com/badges/listed.svg)](https://unitedstatesofamericasuperintelligence.com/open/nemotron-3-ultra-550b-a55b/)

HTML

<a href="https://unitedstatesofamericasuperintelligence.com/open/nemotron-3-ultra-550b-a55b/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/listed.svg" alt="Listed in the USASI catalog" height="20"></a>