Model Spend Arena2ND ED.
753B · MoE · 1,048,576 ctx · 2026-08-14

GLM-5.2

Runs on Data centre · Hugging Face ↗

vLLMSGLangllama.cpp

Coding index 68.8 (Artificial Analysis)

Z.ai's flagship — a very large Mixture-of-Experts (hundreds of billions of total params). One of the strongest open models by coding index, but firmly data-centre scale to run locally, even at Q4 (hundreds of GB).

Sizes on disk

Real GGUF file sizes = weight VRAM. Add the KV cache for your context (≈126 GB at 32K, fp16).

QuantizationSize
Q2_K253.9 GB
Q3_K_M342.7 GB
IQ4_XS365.3 GB
Q4_K_S436.4 GB
Q4_K_M465.8 GB
Q4467.3 GB
Q5_K_M560.8 GB
Q8_0801.4 GB
Q8819.7 GB
Q6_K1310.2 GB
BF161508.0 GB

Config tips

Multi-GPU or a serious server only — a Q4 build is still hundreds of GB of weights plus a large KV cache. Serve with vLLM or SGLang tensor-parallel across cards. For desktops it is far cheaper to rent it per token (see the leaderboard).