No — not on this device
GLM-5.2 744B-A40B at Q4_K_M needs 424.7 GB against 9.7 GB usable, and the shortfall of 415.0 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.
The VRAM budget
weights 423.4 GB
Weights 423.4 GB
KV cache @ 8K 0.69 GB
Runtime overhead 0.6 GB
Over budget 415.0 GB past 9.7 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 745.1 GB | 746.4 GB | — | ~0.4 | −0.1% ppl | 736.7 GB over |
| Q6_K | 575.1 GB | 576.3 GB | — | ~0.5 | −0.4% ppl | 566.6 GB over |
| Q5_K_M | 497.0 GB | 498.3 GB | — | ~0.5 | −0.8% ppl | 488.6 GB over |
| Q4_K_M | 423.4 GB | 424.7 GB | — | ~0.6 | −1.9% ppl | 415.0 GB over |
| Q3_K_M | 342.8 GB | 344.0 GB | — | ~0.8 | −5.4% ppl | 334.3 GB over |
| Q2_K | 293.7 GB | 294.9 GB | — | ~0.9 | −15% ppl | 285.2 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
$ llama-server \
-hf zai-org/GLM-5.2:Q4_K_M \
-c 8192 -ngl 1
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.