QDNAAdvisory and architecture for LLM inference and training platforms, on-premises or hybrid

How much memory does Nemotron 3 Ultra need in FP16?

Nemotron 3 Ultra has 550 billion parameters. The FP16 format decides how much memory is needed to load them.

Short answer. In FP16, the weights of Nemotron 3 Ultra take about 1,265 GB including the runtime margin. 3 of the 8 platforms in the catalogue have enough memory.

How is this footprint calculated?

Nemotron 3 Ultra totals 550 billion parameters. The FP16 format takes 2 byte per parameter (16 bits per parameter, hence 2 bytes). The product gives the weights, to which a 15% runtime margin is added for activations and buffers: 550 billion parameters × 2 bytes (FP16) = 1,100.0 GB of weights; × 1.15 runtime margin = 1,265.0 GB. The attention cache is not calculated on this page. These models’ architectures (compressed latent, linear or sparse attention, Mamba layers) share no per-token formula; it is measured on the machine, with the target context and concurrency [TO BE MEASURED].

What does the format change?

FP16 brings full precision, the quality reference.

FormatWeights in memory Compatible platforms
FP161,265 GB3
FP8632 GB6
NVFP4316 GB7
Q4379 GB7

Which platforms qualify?

See the Nemotron 3 Ultra fact sheet.

How much memory for Nemotron 3 Ultra in FP16?

About 1,265 GB for the weights, excluding the attention cache.

Which format should I choose for Nemotron 3 Ultra?

FP16 brings full precision, the quality reference. The most precise format that fits the target machine remains the best choice.

Method and sources

Memory footprints are calculated, not measured: a reading on real hardware may differ depending on the engine and the exact weight format. Every figure below carries its source and the date of its last check.