NVIDIA Nemotron / NVIDIA Nemotron 3 Ultra 550B-A55B
BF16 quantization for NVIDIA Nemotron 3 Ultra 550B-A55B
The published profile is indicative; engineering measurements are completed for the selected model and hardware.
Before → After
Base releaseVerified checkpoint
550.000B
550.000B
QuantizationBF16
Quality retention target
Quality retention target
Production artifactArtifact
Lineage and benchmark report
Lineage and benchmark report
GPU targeting
Weights and KV cacheEstimated until measured during engineering
Estimated VRAMMeasured
Runtime packagingtransformers
Transparent pricing
Not currently orderable