Can I run this LLM?
Can a NVIDIA L40S (48GB) run Llama 4 Scout (MoE)?
Llama · See model card · estimated for a 48.0 GB machine at 4K context.
Yes, but it's tight.
Best fit: Llama 4 Scout (MoE) at Q2_K · 39.6 GB · 73–109 tok/s on a NVIDIA L40S (48GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 39.6 GB | 73–109 tok/s | Tight / slow |
| Q3_K_M | 51.8 GB | 60–89 tok/s | Won't fit |
| Q4_K_M | 65.4 GB | 50–74 tok/s | Won't fit |
| Q5_K_M | 76.6 GB | 44–65 tok/s | Won't fit |
| Q6_K | 88.4 GB | 39–58 tok/s | Won't fit |
| Q8_0 | 114.5 GB | 31–46 tok/s | Won't fit |
| FP16 | 215.6 GB | 17–26 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA L40S (48GB) runsLlama 4 Scout (MoE) on other machinesWhat to buy to run it →
Ran Llama 4 Scout (MoE) on a NVIDIA L40S (48GB)? Add your real numbers →