Llama 4 Maverick 17B — VRAM Requirements
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 21 lipca 2026
How much GPU VRAM you need to run Llama 4 Llama 4 Maverick 17B by Meta locally, a 400B-parameter model. Figures are quantized weights + KV cache + framework overhead from a memory-bandwidth roofline model.
Llama 4 Maverick 17B needs about 242 GB VRAM at Q4_K_M.
VRAM by Quantization
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 131.5 GB | 132.3 GB |
| Q3_K_M | 3.41 | 170.5 GB | 171.3 GB |
| Q4_K_M | 4.83 | 241.5 GB | 242.3 GB |
| Q5_K_M | 5.67 | 283.5 GB | 284.3 GB |
| Q6_K | 6.56 | 328.0 GB | 328.8 GB |
| Q8_0 | 8.50 | 425.0 GB | 425.8 GB |
| F16 | 16.00 | 800.0 GB | 800.8 GB |
Switch quantization in the interactive calculator, or see the full Llama 4 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-4-maverick-17b)Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.