GLM-4.7-Flash 30B-A3B — VRAM Requirements
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 15 sierpnia 2026
How much GPU VRAM you need to run GLM-4.7 / GLM-Z1 GLM-4.7-Flash 30B-A3B by Zhipu AI (Z.ai) locally, a 30B-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 /pl/methodology.
GLM-4.7-Flash 30B-A3B needs about 19 GB VRAM at Q4_K_M.
VRAM by Quantization
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 9.9 GB | 10.7 GB |
| Q3_K_M | 3.41 | 12.8 GB | 13.6 GB |
| Q4_K_M | 4.83 | 18.1 GB | 18.9 GB |
| Q5_K_M | 5.67 | 21.3 GB | 22.1 GB |
| Q6_K | 6.56 | 24.6 GB | 25.4 GB |
| Q8_0 | 8.50 | 31.9 GB | 32.7 GB |
| F16 | 16.00 | 60.0 GB | 60.8 GB |
Switch quantization in the interactive calculator, or see the full GLM-4.7 / GLM-Z1 model page.
or compare on Vast.ai from $0.35/hr (typical low · varies)
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-4-7-flash-30b-a3b?utm_source=badge&utm_medium=referral&utm_campaign=readme_badge&utm_content=glm-4-7-flash-30b-a3b)Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.