Mistral Large 3 675B-A41B — VRAM Requirements
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 21 lipca 2026
How much GPU VRAM you need to run Mistral Large 3 Mistral Large 3 675B-A41B by Mistral AI locally, a 675B-parameter model. Figures are quantized weights + KV cache + framework overhead from a memory-bandwidth roofline model.
Mistral Large 3 675B-A41B needs about 408 GB VRAM at Q4_K_M.
VRAM by Quantization
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 221.9 GB | 222.7 GB |
| Q3_K_M | 3.41 | 287.7 GB | 288.5 GB |
| Q4_K_M | 4.83 | 407.5 GB | 408.3 GB |
| Q5_K_M | 5.67 | 478.4 GB | 479.2 GB |
| Q6_K | 6.56 | 553.5 GB | 554.3 GB |
| Q8_0 | 8.50 | 717.2 GB | 718.0 GB |
| F16 | 16.00 | 1350.0 GB | 1350.8 GB |
Switch quantization in the interactive calculator, or see the full Mistral Large 3 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-large-3-675b)Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.