Can I run this LLM?
Can a NVIDIA H100 SXM (80GB) run Llama 4 Scout (MoE)?
Llama · See model card · estimated for a 80.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Llama 4 Scout (MoE) at Q3_K_M · 51.8 GB · 158–236 tok/s on a NVIDIA H100 SXM (80GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 39.6 GB | 179–269 tok/s | Runs great |
| Q3_K_M | 51.8 GB | 158–236 tok/s | Runs great |
| Q4_K_M | 65.4 GB | 139–208 tok/s | Tight / slow |
| Q5_K_M | 76.6 GB | 126–189 tok/s | Won't fit |
| Q6_K | 88.4 GB | 115–173 tok/s | Won't fit |
| Q8_0 | 114.5 GB | 97–145 tok/s | Won't fit |
| FP16 | 215.6 GB | 60–89 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA H100 SXM (80GB) runsLlama 4 Scout (MoE) on other machinesWhat to buy to run it →
Ran Llama 4 Scout (MoE) on a NVIDIA H100 SXM (80GB)? Add your real numbers →