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 times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. 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 | AMD MI300X | 7 | $18.40/hr |
| 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.
Cheapest way to run NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 at its published (BF16) precision: 7× AMD MI300X, at $2.63/hr per GPU ($18.40/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16: KV cache by context length
The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.
KV-cache size for NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 is not published for this architecture, so no figure is shown.
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16: common questions
Can NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 run on a single GPU?
No. At BF16 it needs 1252.9 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest capable card in the live feed is a 192.0 GB AMD MI300X, and it takes 7 of them.
How many GPUs do I need to run NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16?
7 at BF16. It needs 1252.9 GB of VRAM and the cheapest capable live offer is a 192.0 GB AMD MI300X, so 7 of them come to $18.40/hr in total.
Does quantizing NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 lower the GPU bill?
Yes. At BF16 the cheapest live fit is 7 AMD MI300X cards at $18.40/hr. At INT4 (quantized) it drops to 7 RTX A6000 cards at $2.54/hr, provided a quantized checkpoint exists for it.
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 (7× AMD MI300X or larger).
- 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.
Weight-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)
Lineage
Quantized and fine-tuned versions
Alternatives at this size
Other models for text-generation within about a third of NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16's 560.5B parameters, from other model lines.
- DeepSeek-R1 (684.5B, F8_E4M3)
- GLM-5.2 (753.3B, BF16)
- Ornith-1.5-397B (403.4B, BF16)
- Llama-3.1-405B (405.9B, BF16)
- A.X-K2 (691.7B, F8_E4M3)
More on NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
Best chat and assistants models: how NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 ranks against the rest.
Compare NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 with DeepSeek-R1, DeepSeek-V3.2, GLM-5.2, DeepSeek-V3-0324, DeepSeek-V3.
Related reading: AMD MI300X pricing and specs, How much VRAM you need for LLMs, Serving LLMs with vLLM, vLLM vs TensorRT-LLM vs SGLang, and Best GPU for LLM inference.
Your own GPU cloud accounts
One console for the GPU clouds you already rent from. Your keys stay on your machine.
$20 a month, flat