How much memory does GLM 5.2 need in NVFP4?

GLM 5.2 has 744 billion parameters. The NVFP4 format decides how much memory is needed to load them.

Short answer. In NVFP4, the weights of GLM 5.2 take about 428 GB including the runtime margin. 7 of the 8 platforms in the catalogue have enough memory.

How is this footprint calculated?

GLM 5.2 totals 744 billion parameters. The NVFP4 format takes 0.5 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?

NVFP4 brings Blackwell format, native FP4 compute.

Format	Weights in memory	Compatible platforms
FP16	1,711 GB	2
FP8	856 GB	4
NVFP4	428 GB	7
Q4	428 GB	7

Which platforms qualify?

See the GLM 5.2 fact sheet.

How much memory for GLM 5.2 in NVFP4?

About 428 GB for the weights, excluding the attention cache.

Which format should I choose for GLM 5.2?

NVFP4 brings Blackwell format, native FP4 compute. 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.