GLM Models — Hardware Requirements
4 GLM models from Z.ai and the community, from the smallest that runs in 0.4 GB of VRAM at Q4 up to 32.6B parameters. Every row links to full quantization tables and GPU compatibility.
All GLM Models by Size
| Model | Params | Runs from (Q4) | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| Xglm 564M | 564M | 0.4 GB | 2K | ||
| Chatglm2 6B | 6B | 6.3 GB | 33K | ||
| Chatglm3 6B | 6.2B | 5.2 GB | 8K | ||
| GLM Z1 32B 0414 | 32.6B | 20.9 GB | 33K |
Frequently Asked Questions
- How much VRAM do I need to run a GLM model?
- The smallest GLM model, Xglm 564M, runs from 0.4 GB of VRAM at Q4_K_M (smaller low-bit quantizations start at 0.3 GB with a noticeable quality loss). Larger family members need proportionally more — see the table above for every model.
- Which GLM models can I run on a 16 GB GPU?
- 3 of 4 GLM models fit in 16 GB of VRAM at Q4_K_M, including Chatglm3 6B, Xglm 564M, Chatglm2 6B.
- What is the most popular GLM model to run locally?
- GLM Z1 32B 0414 is the most downloaded GLM model in local-friendly quantized formats. It runs from 20.9 GB of VRAM at Q4_K_M.