NVIDIA Nemotron 3 Ultra

NVIDIA · nvidia/nvidia-nemotron-3-ultra-550b-a55b

Provider	NVIDIA
Family	nemotron
Type	llm-reasoning
Status	active
Released	2026-06-04
Updated	2026-08-24
Parameters	560.5B
Open weights	yes

Capabilities

Chain Of Thought · tier-2 Function Calling · tier-2 Multilingual · tier-2 Think Budget Control · tier-2

What it fits on

Ordered by predicted speed. Bandwidth sets decode rate; memory decides whether it runs at all.

Every figure here is computed, not measured. Fit is weights at each quantisation against device memory, with a 25% allowance for the KV cache, activations and the OS. Decode rate is the memory-bandwidth roofline at 70% efficiency. Nobody has run this model on these devices.

Device	Memory	Bandwidth	Best quality	Weights	tok/s	Fastest
Apple M3 Ultra	512.0 GB	819.0 GB/s	q5	350.33 GB	~16.7	~20.8 q4

Where it runs

Taken from the card's availability section.

Platform	Id on that platform
DeepInfra	nemotron-3-ultra-550b-a55b
Fireworks AI	accounts/fireworks/models/nemotron-3-ultra-nvfp4
Hugging Face	nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
NVIDIA NIM	nvidia/nemotron-3-ultra-550b-a55b
OpenRouter	nvidia/nemotron-3-ultra-550b-a55b

Verified benchmark evidence

Each row was checked against its source by a reviewer, and carries the model identifier as actually evaluated — which is not always the same as this card's.

Benchmark	Evaluated as	Score	Evidence date	Source kind
aa_lcr	Nemotron 3 Ultra	79.33%	2026-09-10 evaluated	independent evaluator	source
critpt	Nemotron 3 Ultra	3.14%	2026-09-10 evaluated	independent evaluator	source
gdpval_aa	Nemotron 3 Ultra	29.54%	2026-09-10 evaluated	independent evaluator	source
gpqa_diamond	Nemotron 3 Ultra	86.67%	2026-09-10 evaluated	independent evaluator	source
scicode	Nemotron 3 Ultra	40.28%	2026-09-10 evaluated	independent evaluator	source

Reported benchmark scores

This card reports no benchmark scores yet.

Benchmark	Catalogue standing	Score

Data

This card as JSON · See it in the graph · Edit on GitHub