Qwen 2.5 VL 72B Instruct — VRAM Requirements
作者： Jakub Rusinowski · 最后更新： 2026年7月21日
How much GPU VRAM you need to run Qwen 2.5 VL Qwen 2.5 VL 72B Instruct by Alibaba Cloud locally, a 72B-parameter model. Figures are quantized weights + KV cache + framework overhead from a memory-bandwidth roofline model.
Qwen 2.5 VL 72B Instruct needs about 44 GB VRAM at Q4_K_M.
VRAM by Quantization
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 23.7 GB | 24.5 GB |
| Q3_K_M | 3.41 | 30.7 GB | 31.5 GB |
| Q4_K_M | 4.83 | 43.5 GB | 44.3 GB |
| Q5_K_M | 5.67 | 51.0 GB | 51.8 GB |
| Q6_K | 6.56 | 59.0 GB | 59.8 GB |
| Q8_0 | 8.50 | 76.5 GB | 77.3 GB |
| F16 | 16.00 | 144.0 GB | 144.8 GB |
Switch quantization in the interactive calculator, or see the full Qwen 2.5 VL 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/qwen-2.5-vl-72b)Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.