QDNASales and integration of LLM inference and training platforms, on-premises or hybrid

How much memory does Nemotron 3 Ultra need in FP8?

Nemotron 3 Ultra has 550 billion parameters. The FP8 format decides how much memory is needed to load them.

Short answer. In FP8, the weights of Nemotron 3 Ultra take about 632 GB including the runtime margin. 6 of the 8 platforms in the catalogue have enough memory.

How is this footprint calculated?

Nemotron 3 Ultra totals 550 billion parameters. The FP8 format takes 1.0 byte per parameter. The product gives the weights, to which a 15% runtime margin is added for activations and buffers. The attention cache is not included: it grows with context and concurrency.

What does the format change?

FP8 brings negligible loss on most tasks.

FormatWeights in memory Compatible platforms
FP161,265 GB3
FP8632 GB6
NVFP4316 GB7
Q4316 GB7

Which platforms qualify?

See the Nemotron 3 Ultra fact sheet.

How much memory for Nemotron 3 Ultra in FP8?

About 632 GB for the weights, excluding the attention cache.

Which format should I choose for Nemotron 3 Ultra?

FP8 brings negligible loss on most tasks. The most precise format that fits the target machine remains the best choice.

Method

Parameter counts and memory figures come from the site fact sheets. Memory footprints are calculated, not measured: a reading on real hardware may differ depending on the engine and the exact weight format. Prices are indicative and not contractual.