Can I run this LLM?
Can a NVIDIA H100 SXM (80GB) run DeepSeek-R1-Distill 32B?
DeepSeek · Apache 2.0 · estimated for a 80.0 GB machine at 4K context.
Yes — it runs great.
Best fit: DeepSeek-R1-Distill 32B at Q8_0 · 34.8 GB · 58–87 tok/s on a NVIDIA H100 SXM (80GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 12.3 GB | 123–184 tok/s | Runs great |
| Q3_K_M | 15.9 GB | 104–156 tok/s | Runs great |
| Q4_K_M | 19.9 GB | 89–134 tok/s | Runs great |
| Q5_K_M | 23.3 GB | 80–119 tok/s | Runs great |
| Q6_K | 26.9 GB | 71–107 tok/s | Runs great |
| Q8_0 | 34.8 GB | 58–87 tok/s | Runs great |
| FP16 | 65.5 GB | 34–51 tok/s | Tight / slow |
Open the full calculator →Everything a NVIDIA H100 SXM (80GB) runsDeepSeek-R1-Distill 32B on other machinesWhat to buy to run it →
Ran DeepSeek-R1-Distill 32B on a NVIDIA H100 SXM (80GB)? Add your real numbers →