What are the hardware requirements for NVIDIA Nemotron 3 Ultra 550B A55B NVFP4?

NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 requires approximately 63.1 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 and how large is it?

NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 is developed by nvidia, a model with 550b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 perform on standard benchmarks?

NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 has the following published scores: LMSYS ELO 1419. Compare against reference models on this page or on the LLM Explorer leaderboards.

NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 by nvidia — VRAM 63.1GB, 256K context

Name: NVIDIA Nemotron 3 Ultra 550B A55B NVFP4
Author: nvidia

NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 is an open-source language model by nvidia. Features: 550b LLM, VRAM: 63.1GB, Context: 256K, License: other, LLM Explorer Score: 0.54, ELO: 1419.

8-bit Ar Conversational Dataset:nvidia/nemotron-post-t... Dataset:nvidia/nemotron-pre-tr... De Deploy:azure Deploy:sagemaker En Endpoints compatible Es Eval-results Fr He Hi It Ja Ko Latent-moe Modelopt Mtp Nemotron-3 Nemotron h Nvidia Pt Pytorch Region:us Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4

NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 Benchmarks

LMSys ELO 1419 vs 1272 (so35) 11.6%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 Parameters and Internals

LLM Name	NVIDIA Nemotron 3 Ultra 550B A55B NVFP4
Repository 🤗	https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
Model Size	550b
Required VRAM	63.1 GB
Updated	2026-08-04
Maintainer	nvidia
Model Type	nemotron_h
Model Files	2.6 GB: 1-of-113 6.3 GB: 2-of-113 0.4 GB: 3-of-113 6.3 GB: 4-of-113 0.4 GB: 5-of-113 6.3 GB: 6-of-113 0.4 GB: 7-of-113 0.3 GB: 8-of-113 6.3 GB: 9-of-113 0.4 GB: 10-of-113 6.3 GB: 11-of-113 0.4 GB: 12-of-113 6.3 GB: 13-of-113 0.4 GB: 14-of-113 0.3 GB: 15-of-113 6.3 GB: 16-of-113 0.4 GB: 17-of-113 6.3 GB: 18-of-113 0.4 GB: 19-of-113 6.3 GB: 20-of-113
Supported Languages	en fr es it de pt ja ko hi ar zh he
Model Architecture	NemotronHForCausalLM
License	other
Context Length	262144
Model Max Length	262144
Transformers Version	5.3.0
Vocabulary Size	131072

Rank the NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to NVIDIA Nemotron 3 Ultra 550B A55B NVFP4

Best Alternatives	Context / RAM	Downloads	Likes
...emotron 3 Ultra 550B A55B BF16	256K / 204.9 GB	493863	308
...motron 3 Ultra 550B A55B NVFP4	256K / 63.1 GB	103	5
Nemotron 3 Labs Ultra Math SFT	256K / 85.9 GB	510	4
Nemotron 3 Labs Ultra Math RL	256K / 204.9 GB	374	3
...motron 3 Ultra 550B A55B GenRM	256K / 219.9 GB	2666	11
...on 3 Ultra 550B A55B Base BF16	256K / 209.9 GB	1005	29
Nemotron 3 Ultra 550B A55B	256K / 144.3 GB	473	2
...emotron 3 Ultra 550B A55B Base	256K / 209.9 GB	23	2
...DIA Nemotron 3 Ultra 550B A55B	256K / 204.9 GB	19	1
...B Abliterated Uncensored NVFP4	256K / 63.1 GB	582	5