How much VRAM to run GLM-5.2?

About 507 GB atQ4_K_M with an 8K context — beyond any single common device. Full breakdown below, or check your exact hardware.

GLM-5.2 VRAM by quantisation

QuantisationWeightsTotal (8K ctx)Fits on
Q4_K_M459.3 GB507.1 GBmulti-GPU / datacenter only
Q5_K_M536.1 GB591.6 GBmulti-GPU / datacenter only
Q6_K617.5 GB681.0 GBmulti-GPU / datacenter only
Q8_0801.9 GB883.9 GBmulti-GPU / datacenter only
FP16 / BF161506.0 GB1658.4 GBmulti-GPU / datacenter only

Check your hardware

About GLM-5.2

GLM-5.2 is Z.ai's 753B-parameter model released in June 2026, with a 1024K-token context window. It is a mixture-of-experts model: all 753B parameters must sit in memory, but only ~38B are active per token, which is what makes it fast for its size. It uses a latent-attention (MLA) design that compresses its KV cache, keeping even very long contexts cheap in memory: its KV cache is about 0.7 GB at an 8K context, 11.8 GB at 128K, and 94.2 GB at the full 1024K window (FP16 cache).

For most people Q4_K_M is the sweet spot — the most popular quality/size trade-off — while Q8 is near-lossless if you have the memory. Totals above include the KV cache and a realistic framework overhead, so they are what you should expect to see in practice rather than just the download size. Weight sizes are calibrated against real GGUF files — see themethodology.

Frequently asked questions

How much VRAM does GLM-5.2 need?

At Q4_K_M with an 8K context, GLM-5.2 needs about 507 GB (weights 459 GB + KV cache + overhead). No single consumer or workstation device fits it — it needs multi-GPU or datacenter hardware.

Can an RTX 4090 (24GB) run GLM-5.2?

Not fully in VRAM. GLM-5.2 needs about 507 GB even at Q4_K_M, so a 24 GB card would have to offload layers to system RAM at a large speed penalty.

Can a Mac run GLM-5.2?

Not on any current configuration — even a 512 GB Mac Studio's ~384 GB GPU allowance is below the ~507 GB this model needs.

Related

VRAM calculator for any model ·Token counter

Last updated 2026-08-03. Architecture figures from the model's published config.json; see themethodology.