Qwen 3.5 397B-A17B — VRAM Requirements
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 21 lipca 2026
How much GPU VRAM you need to run Qwen 3.5 Qwen 3.5 397B-A17B by Alibaba Cloud locally, a 397B-parameter model. Figures are quantized weights + KV cache + framework overhead from a memory-bandwidth roofline model.
Qwen 3.5 397B-A17B needs about 240 GB VRAM at Q4_K_M.
VRAM by Quantization
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 130.5 GB | 131.3 GB |
| Q3_K_M | 3.41 | 169.2 GB | 170.0 GB |
| Q4_K_M | 4.83 | 239.7 GB | 240.5 GB |
| Q5_K_M | 5.67 | 281.4 GB | 282.2 GB |
| Q6_K | 6.56 | 325.5 GB | 326.3 GB |
| Q8_0 | 8.50 | 421.8 GB | 422.6 GB |
| F16 | 16.00 | 794.0 GB | 794.8 GB |
Switch quantization in the interactive calculator, or see the full Qwen 3.5 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/qwen3-5-397b-a17b)Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.