GLM-5 744B — VRAM Requirements
作者： Jakub Rusinowski · 最后更新： 2026年7月21日
How much GPU VRAM you need to run GLM-5 / GLM-5.1 GLM-5 744B by Zhipu AI locally, a 744B-parameter model. Figures are quantized weights + KV cache + framework overhead from a memory-bandwidth roofline model.
GLM-5 744B needs about 450 GB VRAM at Q4_K_M.
VRAM by Quantization
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 244.6 GB | 245.4 GB |
| Q3_K_M | 3.41 | 317.1 GB | 317.9 GB |
| Q4_K_M | 4.83 | 449.2 GB | 450.0 GB |
| Q5_K_M | 5.67 | 527.3 GB | 528.1 GB |
| Q6_K | 6.56 | 610.1 GB | 610.9 GB |
| Q8_0 | 8.50 | 790.5 GB | 791.3 GB |
| F16 | 16.00 | 1488.0 GB | 1488.8 GB |
Switch quantization in the interactive calculator, or see the full GLM-5 / GLM-5.1 model page.
Add this badge to your model card
Model creators: paste this into your Hugging Face model card README to link readers straight to this VRAM breakdown.
[](https://llmconfigurator.com/en/vram-calculator/glm-5-744b)Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.