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

Running Nemotron 3 Ultra on B300 SXM

Nemotron 3 Ultra has 550 billion parameters. B300 SXM offers 2,304 GB of HBM3e across 8 GPUs memory. This page puts the two side by side.

Short answer. Nemotron 3 Ultra fits comfortably on B300 SXM. In FP16, its weights take about 1,265 GB of the 2,304 GB available, leaving 1,039 GB for the attention cache and concurrency.

How much memory does Nemotron 3 Ultra need?

Weights take the parameter count multiplied by the format size, plus a 15% runtime margin for activations and buffers. The attention cache sits on top: it grows with context length and with the number of concurrent requests, so it is sized case by case.

FormatWeights in memory On this machineWhat the format costs
FP161,265 GBfitsfull precision, the quality reference
FP8632 GBfitsnegligible loss on most tasks
NVFP4316 GBfitsBlackwell format, native FP4 compute
Q4316 GBfitsblock quantisation, broadly supported

Nemotron 3 Ultra activates 55 billion parameters per token out of 550 billion. Active parameters govern speed, not footprint: every expert stays resident in memory. Confusing the two under-sizes the machine by an order of magnitude.

What is left to serve requests?

Nemotron 3 Ultra fits comfortably on B300 SXM. In FP16, its weights take about 1,265 GB of the 2,304 GB available, leaving 1,039 GB for the attention cache and concurrency. The remaining margin decides how many concurrent requests and how much context the machine sustains. A margin below a quarter of memory forces a limit on context or on concurrency.

B300 SXM ranges from 500 to 800 k€, indicative and not contractual. The machine targets the GE segment.

Where else can Nemotron 3 Ultra run?

See the Nemotron 3 Ultra and B300 SXM fact sheets.

How much memory does Nemotron 3 Ultra need?

In FP16, weights take about 1,265 GB including the runtime margin. The attention cache sits on top and depends on context.

Does Nemotron 3 Ultra fit on B300 SXM?

Nemotron 3 Ultra fits comfortably on B300 SXM. In FP16, its weights take about 1,265 GB of the 2,304 GB available, leaving 1,039 GB for the attention cache and concurrency.

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.