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

Running GLM 5.2 on GB300 NVL72

GLM 5.2 has 744 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. GLM 5.2 fits comfortably on GB300 NVL72. In FP16, its weights take about 1,711 GB of the 20,700 GB available, leaving 18,989 GB for the attention cache and concurrency.

How much memory does GLM 5.2 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
FP161,711 GBfitsfull precision, the quality reference
FP8856 GBfitsnegligible loss on most tasks
NVFP4428 GBfitsBlackwell format, native FP4 compute
Q4428 GBfitsblock quantisation, broadly supported

What is left to serve requests?

GLM 5.2 fits comfortably on GB300 NVL72. In FP16, its weights take about 1,711 GB of the 20,700 GB available, leaving 18,989 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 GLM 5.2 run?

See the GLM 5.2 and GB300 NVL72 fact sheets.

How much memory does GLM 5.2 need?

In FP16, weights take about 1,711 GB including the runtime margin. The attention cache sits on top and depends on context.

Does GLM 5.2 fit on GB300 NVL72?

GLM 5.2 fits comfortably on GB300 NVL72. In FP16, its weights take about 1,711 GB of the 20,700 GB available, leaving 18,989 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.