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

Running MiniMax M3 on GB300 NVL72

MiniMax M3 has 428 billion parameters. GB300 NVL72 offers 20,700 GB of HBM3e across a 72-GPU rack memory. This page puts the two side by side.

Short answer. MiniMax M3 fits comfortably on GB300 NVL72. In FP16, its weights take about 984 GB of the 20,700 GB available, leaving 19,716 GB for the attention cache and concurrency.

How much memory does MiniMax M3 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
FP16984 GBfitsfull precision, the quality reference
FP8492 GBfitsnegligible loss on most tasks
NVFP4246 GBfitsBlackwell format, native FP4 compute
Q4246 GBfitsblock quantisation, broadly supported

MiniMax M3 activates 23 billion parameters per token out of 428 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?

MiniMax M3 fits comfortably on GB300 NVL72. In FP16, its weights take about 984 GB of the 20,700 GB available, leaving 19,716 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.

GB300 NVL72 ranges from from 3,9 M€, indicative and not contractual. The machine targets the GE segment.

Where else can MiniMax M3 run?

See the MiniMax M3 and GB300 NVL72 fact sheets.

How much memory does MiniMax M3 need?

In FP16, weights take about 984 GB including the runtime margin. The attention cache sits on top and depends on context.

Does MiniMax M3 fit on GB300 NVL72?

MiniMax M3 fits comfortably on GB300 NVL72. In FP16, its weights take about 984 GB of the 20,700 GB available, leaving 19,716 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.