Will this model run on your hardware?
Can I run Z.ai: GLM 4.6V locally?
- 108B parameters (12B active, MoE)
- context up to 128K
- licence: mit
- Weights: zai-org/GLM-4.6V · GGUF: unsloth/GLM-4.6V-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 | 113.6 GB |
| Q6_K | 95.9 GB |
| Q5_K_M | 80.8 GB |
| Q4_K_M | 70.6 GB |
| Q3_K_M | 55.4 GB |
| Q2_K | 43.9 GB |
Run it locally
ollama run hf.co/unsloth/GLM-4.6V-GGUF:Q4_K_M
llama serve -hf unsloth/GLM-4.6V-GGUF:Q4_K_M
LM Studio: open unsloth/GLM-4.6V-GGUF