Llama 3.2 Vision 90B — VRAM Requirements
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 21 lipca 2026
How much GPU VRAM you need to run Llama 3.2 Vision Llama 3.2 Vision 90B by Meta locally, a 90B-parameter model. Figures are quantized weights + KV cache + framework overhead from a memory-bandwidth roofline model.
Llama 3.2 Vision 90B needs about 55 GB VRAM at Q4_K_M.
VRAM by Quantization
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 29.6 GB | 30.4 GB |
| Q3_K_M | 3.41 | 38.4 GB | 39.2 GB |
| Q4_K_M | 4.83 | 54.3 GB | 55.1 GB |
| Q5_K_M | 5.67 | 63.8 GB | 64.6 GB |
| Q6_K | 6.56 | 73.8 GB | 74.6 GB |
| Q8_0 | 8.50 | 95.6 GB | 96.4 GB |
| F16 | 16.00 | 180.0 GB | 180.8 GB |
Switch quantization in the interactive calculator, or see the full Llama 3.2 Vision 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/llama-3.2-vision-90b)Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.