No — not on this device

GLM-5.2 744B-A40B at Q4_K_M needs 424.7 GB against 139.4 GB usable, and the shortfall of 285.3 GB is more than 64 GB of system RAM can cover at a tolerable speed. A smaller sibling or a lower quantisation is the honest answer here.

Does not fit 8K context Q4_K_M · 423.4 GB MIT Released 13 Jun 2026 Not in the Ollama library

The strongest all-round open-weight model of mid-2026 on most public boards. Listed as a ceiling: 512 GB of unified memory at Q4.

What hardware do I need for GLM-5.2 744B-A40B? →

Fits instead: GLM-4.7-Flash 30B-A3B (18.6 GB)

The VRAM budget

weights 423.4 GB
Weights 423.4 GB KV cache @ 8K 0.69 GB Runtime overhead 0.6 GB Over budget 285.3 GB past 139.4 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 745.1 GB 746.4 GB ~0.4 −0.1% ppl 607.0 GB over
Q6_K 575.1 GB 576.3 GB ~0.6 −0.4% ppl 436.9 GB over
Q5_K_M 497.0 GB 498.3 GB ~0.7 −0.8% ppl 358.9 GB over
Q4_K_M 423.4 GB 424.7 GB ~0.9 −1.9% ppl 285.3 GB over
Q3_K_M 342.8 GB 344.0 GB ~1.3 −5.4% ppl 204.6 GB over
Q2_K 293.7 GB 294.9 GB ~1.7 −15% ppl 155.5 GB over

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model uses multi-head latent attention, so its cache is a compressed latent rather than full K and V.

How to run it

terminal
$ llama-server \
    -hf zai-org/GLM-5.2:Q4_K_M \
    -c 8192 -ngl 25

The engine underneath most of the others. Every knob is exposed. More on llama.cpp.

01Download is 423.4 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.
03If it falls back to CPU silently, drop the context first, then step down a quantisation.
See all models for this rig Compare with another model