Can I run this LLM?
Can a NVIDIA H100 SXM (80GB) run Qwen3.8 27B?
Qwen · Apache 2.0 · estimated for a 80.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.8 27B at FP16 · 54.7 GB · 40–60 tok/s on a NVIDIA H100 SXM (80GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 10.8 GB | 139–208 tok/s | Runs great |
| Q3_K_M | 13.4 GB | 121–182 tok/s | Runs great |
| Q4_K_M | 17.4 GB | 101–152 tok/s | Runs great |
| Q5_K_M | 20.9 GB | 89–133 tok/s | Runs great |
| Q6_K | 23.9 GB | 80–120 tok/s | Runs great |
| Q8_0 | 29.1 GB | 68–103 tok/s | Runs great |
| FP16 | 54.7 GB | 40–60 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA H100 SXM (80GB) runsQwen3.8 27B on other machinesWhat to buy to run it →
Ran Qwen3.8 27B on a NVIDIA H100 SXM (80GB)? Add your real numbers →