Will this model run on your hardware?
Can I run Z.ai: GLM 5.2 locally?
- 753B parameters (60B active, MoE)
- context up to 1024K
- licence: mit
- Weights: zai-org/GLM-5.2 · GGUF: unsloth/GLM-5.2-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 801.4 GB |
| UD-Q6_K | 625.9 GB |
| UD-Q5_K_M | 560.8 GB |
| UD-Q4_K_M | 465.8 GB |
| UD-Q3_K_M | 342.7 GB |
Run it locally
ollama run hf.co/unsloth/GLM-5.2-GGUF:UD-Q4_K_M
llama serve -hf unsloth/GLM-5.2-GGUF:UD-Q4_K_M
LM Studio: open unsloth/GLM-5.2-GGUF