How much memory does GLM 5.2 need in Q4?

GLM 5.2 has 744 billion parameters. The Q4 format decides how much memory is needed to load them.

By QDNA · Published on 27 July 2026 · Updated on 15 September 2026

Short answer. In Q4, the weights of GLM 5.2 take about 513 GB including the runtime margin. 6 of the 8 platforms in the catalogue have enough memory.

How is this footprint calculated?

GLM 5.2 totals 744 billion parameters. The Q4 format takes 0.6 byte per parameter (taken here as llama.cpp Q4_K_M, 0.6 byte per parameter including scales; Q4_K_S weighs 0.56, AWQ and GPTQ 0.55). The product gives the weights, to which a 15% runtime margin is added for activations and buffers: 744 billion parameters × 0.6 byte (Q4) = 446.4 GB of weights; × 1.15 runtime margin = 513.4 GB. The attention cache is not calculated on this page. These models’ architectures (compressed latent, linear or sparse attention, Mamba layers) share no per-token formula; it is measured on the machine, with the target context and concurrency [TO BE MEASURED].

What does the format change?

Q4 brings block quantisation, broadly supported.

Format	Weights in memory	Compatible platforms
FP16	1,711 GB	2
FP8	856 GB	4
NVFP4	428 GB	7
Q4	513 GB	6

Which platforms qualify?

See the GLM 5.2 fact sheet.

How much memory for GLM 5.2 in Q4?

About 513 GB for the weights, excluding the attention cache.

Which format should I choose for GLM 5.2?

Q4 brings block quantisation, broadly supported. The most precise format that fits the target machine remains the best choice.

Method and sources

Memory footprints are calculated, not measured: a reading on real hardware may differ depending on the engine and the exact weight format. Every figure below carries its source and the date of its last check.

GLM 5.2: 744 billion parameters, 40 billion active, 1,048,576-token context, MIT licence. Hugging Face repository (config.json, API, model card), checked on 2 September 2026. 744 billion announced by Z.AI; the repository holds 753 billion tensor elements in BF16 (1,507 GB).
Bytes per parameter: FP16 2 (16 bits per parameter, hence 2 bytes); FP8 1 (8 bits per parameter (E4M3), hence 1 byte, block scales not counted); NVFP4 0.5 (4 bits per parameter, hence 0.5 byte; 4-bit published weights weigh 0.54 to 0.56 byte per parameter with their scales (DeepSeek V4 Pro 865 GB for 1,599 billion, Kimi K3 1,561 GB for 2,780 billion)); Q4 0.6 (taken here as llama.cpp Q4_K_M, 0.6 byte per parameter including scales; Q4_K_S weighs 0.56, AWQ and GPTQ 0.55). Source: connaissance/faits.yaml, quantifications family, checked on 2026-08-31.
Runtime margin × 1.15: QDNA operating assumption, not measured: 15% above the weights for activations, buffers and fragmentation.
“Fits” threshold at 75% of memory: QDNA assumption, not measured, which keeps the remaining quarter for the attention cache and concurrency.