Can I run this LLM?
Can a NVIDIA H100 SXM (80GB) run DeepSeek-R1-Distill 14B?
DeepSeek · Apache 2.0 · estimated for a 80.0 GB machine at 4K context.
Yes — it runs great.
Best fit: DeepSeek-R1-Distill 14B at FP16 · 29.6 GB · 67–100 tok/s on a NVIDIA H100 SXM (80GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 5.8 GB | 186–279 tok/s | Runs great |
| Q3_K_M | 7.3 GB | 166–249 tok/s | Runs great |
| Q4_K_M | 9.0 GB | 150–224 tok/s | Runs great |
| Q5_K_M | 10.5 GB | 137–206 tok/s | Runs great |
| Q6_K | 12.1 GB | 126–189 tok/s | Runs great |
| Q8_0 | 15.7 GB | 106–160 tok/s | Runs great |
| FP16 | 29.6 GB | 67–100 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA H100 SXM (80GB) runsDeepSeek-R1-Distill 14B on other machinesWhat to buy to run it →
Ran DeepSeek-R1-Distill 14B on a NVIDIA H100 SXM (80GB)? Add your real numbers →