What are the hardware requirements for Nemotron 3 Ultra 550B A55B 4bit?

Nemotron 3 Ultra 550B A55B 4bit requires approximately 130 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 Nemotron 3 Ultra 550B A55B 4bit and how large is it?

Nemotron 3 Ultra 550B A55B 4bit is developed by mlx-community, a model with 550b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Nemotron 3 Ultra 550B A55B 4bit?

Nemotron 3 Ultra 550B A55B 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Nemotron 3 Ultra 550B A55B 4bit by mlx-community — VRAM 130GB, 256K context

Name: Nemotron 3 Ultra 550B A55B 4bit
Author: mlx-community

Nemotron 3 Ultra 550B A55B 4bit is an open-source language model by mlx-community. Features: 550b LLM, VRAM: 130GB, Context: 256K, License: other, Quantized, LLM Explorer Score: 0.26.

4-bit 4bit Base model:nvidia/nvidia-nemot... Base model:quantized:nvidia/nv... Conversational Custom code Mlx Nemotron Nemotron h Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/Nemotron-3-Ultra-550B-A55B-4bit

Nemotron 3 Ultra 550B A55B 4bit Parameters and Internals

LLM Name	Nemotron 3 Ultra 550B A55B 4bit
Repository 🤗	https://huggingface.co/mlx-community/Nemotron-3-Ultra-550B-A55B-4bit
Base Model(s)	...emotron 3 Ultra 550B A55B BF16 nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
Model Size	550b
Required VRAM	130 GB
Updated	2026-08-02
Maintainer	mlx-community
Model Type	nemotron_h
Model Files	3.0 GB: 1-of-109 1.6 GB: 2-of-109 1.7 GB: 3-of-109 1.7 GB: 4-of-109 1.7 GB: 5-of-109 1.7 GB: 6-of-109 1.7 GB: 7-of-109 1.7 GB: 8-of-109 1.7 GB: 9-of-109 1.7 GB: 10-of-109 1.7 GB: 11-of-109 1.7 GB: 12-of-109 3.0 GB: 13-of-109 3.4 GB: 14-of-109 3.4 GB: 15-of-109 3.4 GB: 16-of-109 3.4 GB: 17-of-109 3.4 GB: 18-of-109 3.4 GB: 19-of-109 3.4 GB: 20-of-109 3.4 GB: 21-of-109 3.4 GB: 22-of-109 3.4 GB: 23-of-109 3.4 GB: 24-of-109 3.4 GB: 25-of-109 3.4 GB: 26-of-109 3.4 GB: 27-of-109 3.4 GB: 28-of-109 3.4 GB: 29-of-109 3.4 GB: 30-of-109 3.4 GB: 31-of-109 3.4 GB: 32-of-109 3.4 GB: 33-of-109 3.4 GB: 34-of-109 3.4 GB: 35-of-109 3.4 GB: 36-of-109 3.4 GB: 37-of-109 3.4 GB: 38-of-109 3.4 GB: 39-of-109 3.4 GB: 40-of-109 3.4 GB: 41-of-109 3.4 GB: 42-of-109 3.4 GB: 43-of-109 3.4 GB: 44-of-109
Quantization Type	4bit
Model Architecture	NemotronHForCausalLM
License	other
Context Length	262144
Model Max Length	262144
Transformers Version	5.3.0
Vocabulary Size	131072

Rank the Nemotron 3 Ultra 550B A55B 4bit 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 Nemotron 3 Ultra 550B A55B 4bit

Best Alternatives	Context / RAM	Downloads	Likes
...motron 3 Ultra 550B A55B NVFP4	256K / 63.1 GB	240041	277
...emotron 3 Ultra 550B A55B GGUF	256K / GB	7251	35
...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

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Nemotron-3-Ultra-550B-A55B-4bit.