NVIDIANVIDIA Nemotron 3 Ultra 550B A55B
NVIDIA Nemotron 3 Ultra 550B A55B BF16 is a 550-billion parameter chat model built by NVIDIA, utilizing a hybrid LatentMoE architecture that combines Mamba-2, Mixture of Experts (MoE), and Attention with Multi-Token Prediction. It is designed for frontier reasoning, complex agentic workflows, and long-context analysis.
Input
Output
Context
512K
Max Output
128K
Parameters
560.5B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Loading capabilities…
Benchmarks
Resources & Links
Estimated GPU requirements for NVIDIA Nemotron 3 Ultra 550B A55B
Estimates based on INT8 quantization at up to 32K context. A count above one assumes tensor parallelism across the cards. Actual requirements vary by framework and configuration.
More models by NVIDIA
The creator's other models in the catalog, with their context, size and license where published.
Compare it, or keep browsing
Put this model beside its alternatives on the same evidence, or go back to the full catalog.
Frequently asked questions about NVIDIA Nemotron 3 Ultra 550B A55B
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
NVIDIA Nemotron 3 Ultra 550B A55B advertises a context window of 512,288 tokens, with a maximum output of 128,000 tokens in a single response. The figure is the creator's published maximum; a given provider may serve less, and the gateway routes on what each provider actually serves.
Yes. NVIDIA Nemotron 3 Ultra 550B A55B is an open-weight model released under the Other license, so the weights can be downloaded and self-hosted within that license's terms.
NVIDIA Nemotron 3 Ultra 550B A55B accepts Text and produces Text. The capabilities card on this page lists which API features each deployment honours, such as function calling and structured output, with the source each was checked against.
NVIDIA Nemotron 3 Ultra 550B A55B has published results from Artificial Analysis, shown by suite in the benchmarks card above exactly as the publisher reported them. Scores are not combined across suites, and a suite that has not measured NVIDIA Nemotron 3 Ultra 550B A55B is shown as not available rather than estimated.
Not on the managed pool today; NVIDIA Nemotron 3 Ultra 550B A55B is listed for reference and comparison. Connect your own provider key or endpoint that serves it and the gateway runs it on your account, with routing decisions recorded the same way.
About 550.4 GB at INT8 for the weights and a default context, from the catalog's 560.5B parameter count; FP16 needs roughly twice that, and long contexts or many concurrent requests add KV cache on top. The GPU section on this page lists cards that hold it, and the capacity planner sizes it for your context length and traffic.
Fields collected from public registries, provider APIs and benchmark publishers, each tagged with its source.
Last updated: Nov 6, 2026
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start on the free plan with 5,000 requests a month, no card required.