Mistral NeMo 12B — VRAM Requirements
作者： Jakub Rusinowski · 最后更新： 2026年7月21日
How much GPU VRAM you need to run Mistral Family Mistral NeMo 12B by Mistral AI locally, a 12B-parameter model. Figures are quantized weights + KV cache + framework overhead from a memory-bandwidth roofline model.
Mistral NeMo 12B needs about 9 GB VRAM at Q4_K_M.
VRAM by Quantization
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 3.9 GB | 6.1 GB |
| Q3_K_M | 3.41 | 5.1 GB | 7.3 GB |
| Q4_K_M | 4.83 | 7.2 GB | 9.4 GB |
| Q5_K_M | 5.67 | 8.5 GB | 10.6 GB |
| Q6_K | 6.56 | 9.8 GB | 12.0 GB |
| Q8_0 | 8.50 | 12.8 GB | 14.9 GB |
| F16 | 16.00 | 24.0 GB | 26.1 GB |
Switch quantization in the interactive calculator, or see the full Mistral Family 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/mistral-nemo)Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.