Written by Jakub Rusinowski · Last updated September 11, 2026
How much GPU VRAM you need to run GLM-5.3-Flash GLM-5.3-Flash 320B-A18B by Zhipu AI (Z.ai) locally, a 320B-parameter model. Figures are quantized weights + KV cache + framework overhead, computed from the model's parameter count and published architecture — not a throughput model. See /en/methodology.
GLM-5.3-Flash 320B-A18B needs about 194 GB VRAM at Q4_K_M.
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 105.2 GB | 106.0 GB |
| Q3_K_M | 3.41 | 136.4 GB | 137.2 GB |
| Q4_K_M | 4.83 | 193.2 GB | 194.0 GB |
| Q5_K_M | 5.67 | 226.8 GB | 227.6 GB |
| Q6_K | 6.56 | 262.4 GB | 263.2 GB |
| Q8_0 | 8.50 | 340.0 GB | 340.8 GB |
| F16 | 16.00 | 640.0 GB | 640.8 GB |
Switch quantization in the interactive calculator, or see the full GLM-5.3-Flash model page.
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
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-5-3-flash-320b-a18b?utm_source=badge&utm_medium=referral&utm_campaign=readme_badge&utm_content=glm-5-3-flash-320b-a18b)
Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.