GLM-6 355B-A32B — VRAM Requirements
Written by Jakub Rusinowski · Last updated June 26, 2026
How much GPU VRAM you need to run GLM-6 GLM-6 355B-A32B by Zhipu AI (Z.ai) locally, a 355B-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-6 355B-A32B needs about 215 GB VRAM at Q4_K_M.
VRAM by Quantization
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 116.7 GB | 117.5 GB |
| Q3_K_M | 3.41 | 151.3 GB | 152.1 GB |
| Q4_K_M | 4.83 | 214.3 GB | 215.1 GB |
| Q5_K_M | 5.67 | 251.6 GB | 252.4 GB |
| Q6_K | 6.56 | 291.1 GB | 291.9 GB |
| Q8_0 | 8.50 | 377.2 GB | 378.0 GB |
| F16 | 16.00 | 710.0 GB | 710.8 GB |
Switch quantization in the interactive calculator, or see the full GLM-6 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.
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-6-355b-a32b?utm_source=badge&utm_medium=referral&utm_campaign=readme_badge&utm_content=glm-6-355b-a32b)Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.