Can I run this LLM?
Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run DeepSeek-R1-Distill 8B?
DeepSeek · Llama 3.1 Community · estimated for a 144.0 GB machine at 4K context.
Yes — it runs great.
Best fit: DeepSeek-R1-Distill 8B at FP16 · 16.1 GB · 137–205 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 3.2 GB | 267–400 tok/s | Runs great |
| Q3_K_M | 4.0 GB | 251–376 tok/s | Runs great |
| Q4_K_M | 4.9 GB | 236–354 tok/s | Runs great |
| Q5_K_M | 5.7 GB | 224–337 tok/s | Runs great |
| Q6_K | 6.6 GB | 213–319 tok/s | Runs great |
| Q8_0 | 8.5 GB | 191–287 tok/s | Runs great |
| FP16 | 16.1 GB | 137–205 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) runsDeepSeek-R1-Distill 8B on other machinesWhat to buy to run it →
Ran DeepSeek-R1-Distill 8B on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →