QDNAAdvisory and architecture for LLM inference and training platforms, on-premises or hybrid

Running GLM 5.2 on Mac Studio Ultra

GLM 5.2 has 744 billion parameters. Mac Studio Ultra offers 512 GB of Apple unified memory. This page puts the two side by side.

Short answer. GLM 5.2 barely fits on Mac Studio Ultra. In NVFP4, its weights take about 428 GB against 512 GB available. The 84.2 GB margin disappears quickly as context grows.

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. In NVFP4 the calculation reads: 744 billion parameters × 0.5 byte (NVFP4) = 372.0 GB of weights; × 1.15 runtime margin = 427.8 GB. 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 GBdoes not fitfull precision, the quality reference
FP8856 GBdoes not fitnegligible loss on most tasks
NVFP4428 GBtightBlackwell format, native FP4 compute
Q4513 GBdoes not fitblock quantisation, broadly supported

Model sheet: 744 billion parameters, 40 billion active per token, 1,048,576-token context, MIT licence. 744 billion announced by Z.AI; the repository holds 753 billion tensor elements in BF16 (1,507 GB).

GLM 5.2 activates 40 billion parameters per token out of 744 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?

GLM 5.2 barely fits on Mac Studio Ultra. In NVFP4, its weights take about 428 GB against 512 GB available. The 84.2 GB margin disappears quickly as context grows. The remaining margin decides how many concurrent requests and how much context the machine sustains. By QDNA convention a machine “fits” when the weights take at most 75% of its memory; beyond that it “barely fits” and forces a limit on context or on concurrency. 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].

Mac Studio Ultra: indicative price €6,599 to €20,679 incl. VAT, not contractual. Source: Apple Store France as reported by MacGeneration on 25 August 2026: €6,599 for the M5 Ultra with 96 GB, €20,679 with 256 GB and 16 TB; the 512 GB variant is not priced yet. The machine targets the TPE, PME segment.

Where else can GLM 5.2 run?

See the GLM 5.2 and Mac Studio Ultra fact sheets.

How much memory does GLM 5.2 need?

In NVFP4, weights take about 428 GB including the runtime margin. The attention cache sits on top and depends on context.

Does GLM 5.2 fit on Mac Studio Ultra?

GLM 5.2 barely fits on Mac Studio Ultra. In NVFP4, its weights take about 428 GB against 512 GB available. The 84.2 GB margin disappears quickly as context grows.

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.