DeepSeek R1 Distill Qwen 32B — VRAM Requirements
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 21 lipca 2026
How much GPU VRAM you need to run DeepSeek R1 DeepSeek R1 Distill Qwen 32B by DeepSeek locally, a 32B-parameter model. Figures are quantized weights + KV cache + framework overhead from a memory-bandwidth roofline model.
DeepSeek R1 Distill Qwen 32B needs about 22 GB VRAM at Q4_K_M.
VRAM by Quantization
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 10.5 GB | 13.5 GB |
| Q3_K_M | 3.41 | 13.6 GB | 16.6 GB |
| Q4_K_M | 4.83 | 19.3 GB | 22.3 GB |
| Q5_K_M | 5.67 | 22.7 GB | 25.6 GB |
| Q6_K | 6.56 | 26.2 GB | 29.2 GB |
| Q8_0 | 8.50 | 34.0 GB | 36.9 GB |
| F16 | 16.00 | 64.0 GB | 66.9 GB |
Switch quantization in the interactive calculator, or see the full DeepSeek R1 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/deepseek-r1-distill-32b)Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.