Written by Jakub Rusinowski · Last updated August 15, 2026
Not at Q4_K_M — that needs 65.8 GB and the NVIDIA L40S has 48 GB. Drop to Q2_K and it fits in 38.2 GB, with up to 32K of context.
| Model | Llama 4 Scout 17B |
| Parameters | 17B active / 109B total |
| Quantization | Q4_K_M |
| VRAM needed | 65.8 GB |
| NVIDIA L40S VRAM | 48 GB |
| Verdict | Runs at a lower quant |
| Fits at | Q2_K (38.2 GB) |
| Max context | 32K |
Quantize to Q2_K. That is the cheapest fix — it costs some quality but no money.
Running Llama 4 Scout 17B on this card:
Llama 4 Scout 17B needs ~66 GB but this GPU has 48 GB. Rent a A100 (80 GB)-class GPU by the hour instead of buying one:
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
All Llama 4 sizes on the NVIDIA L40S | VRAM calculator for Llama 4 Scout 17B | NVIDIA L40S GPU page | Check your hardware