What GPU do I need to run nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16?
A 550B (MoE) language model for chat and agentic tool use. 560.5B parameters, published in BF16. View on Hugging Face
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 is published by nvidia on Hugging Face, with 287,095 downloads and 337 likes to date. It's a NemotronHForCausalLM model built for text-generation, published natively in BF16.
What NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 is
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 is a 550B-parameter mixture-of-experts language model published by NVIDIA on Hugging Face, part of the Nemotron 3 family. It is released under NVIDIA's own OpenMDW-1.1 license.
License note: NVIDIA's own open model license; read the linked terms before commercial use. Facts in this section are sourced from NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16's Hugging Face model card, not benchmarked by Aquanode.
What it's used for
- Chat assistants
- Agentic tool use and function calling
- Long-context reasoning
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 1044.1 GB | 1252.9 GB | No capable live offer found | – | – |
| FP8 (quantized) | 522.0 GB | 626.4 GB | RTX PRO 6000 | 7 | $9.63/hr |
| INT4 (quantized) | 261.0 GB | 313.2 GB | RTX A6000 | 7 | $2.54/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16: common questions
Can NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 run on a single GPU?
Not on a desktop card. At BF16 it needs 1252.9 GB of VRAM, more than a single 32 GB desktop card holds. No card currently listed on the marketplace both supports BF16 and has enough VRAM for it, so how many it would take is not something this page can answer today.
How to run NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
Run NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 with vLLM
From nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16's own model card (8x GPU single-node recipe, trimmed).
docker run -d --name nemotron-ultra-vllm \
--gpus all \
--ipc=host \
--network=host \
-v $MODEL_CKPT:/model:ro \
vllm/vllm-openai:v0.22.0 \
/model \
--host 0.0.0.0 \
--port 8000 \
--served-model-name nvidia/nemotron-3-ultra \
--trust-remote-code \
--tensor-parallel-size 8 \
--enable-expert-parallel \
--dtype bfloat16 \
--max-model-len 262144Source: https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16/raw/main/README.md
Deploy NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 on Aquanode
Aquanode has no one-click deploy template for NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch a bare GPU pod sized to the requirement above (1253 GB VRAM or more).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch a GPU podWeight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Nemotron 3 models
- NVIDIA-Nemotron-3-Ultra-550B-A55B-FP8-block (560.5B, F8_E4M3)
- NVIDIA-Nemotron-3-Super-120B-A12B-BF16 (123.6B, BF16)
- NVIDIA-Nemotron-3-Super-120B-A12B-FP8 (123.6B, F8_E4M3)
- NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16 (123.6B, BF16)
- NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 (31.6B, F8_E4M3)
Related reading: H100 pricing and specs, The best GPUs for AI, ranked, and Best GPU for LLM inference.
