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.
Runs greatBest fit: DeepSeek-R1-Distill 8B at FP16 · 16.1 GB weights · 137–205 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).
Arena Text Overall · style-controlled
UnratedNo exact matchNo reviewed exact Arena match
No reviewed exact model/configuration match in the Arena Text Overall style-controlled snapshot. No family or editorial score is substituted. Local quantization quality is unmeasured.
Snapshot published 2026-10-08 · snapshot imported 2026-10-11 UTC · validated last-good data · manual refresh
Arena leaderboard dataset · Arena / lmarena-ai, Arena Leaderboard Dataset (CC BY 4.0). Selected Text Overall style-controlled rows; field names adapted, ratings unchanged. · dataset CC BY 4.0 · revision e16f90232986
- Total memory at 4K context
- 17.4 GB
- Weights + KV cache + runtime overhead
- Estimated generation
- 137–205 tok/s
- Estimated first token
- ~0.4s
Every quantization on this machine
On small screens, each quant lists every metric below its name. On wider screens, scroll sideways for total memory, speed and fit. Keyboard: focus the table, then use the arrow keys. Quant names stay visible.
| Quant | Weights | Total memory | Speed | Fit |
|---|---|---|---|---|
| Q2_K | 3.2 GB | 4.5 GB | 267–400 tok/s | Runs great |
| Q3_K_M | 4.0 GB | 5.4 GB | 251–376 tok/s | Runs great |
| Q4_K_M | 4.9 GB | 6.3 GB | 236–354 tok/s | Runs great |
| Q5_K_M | 5.7 GB | 7.1 GB | 224–337 tok/s | Runs great |
| Q6_K | 6.6 GB | 7.9 GB | 213–319 tok/s | Runs great |
| Q8_0 | 8.5 GB | 9.9 GB | 191–287 tok/s | Runs great |
| FP16 | 16.1 GB | 17.4 GB | 137–205 tok/s | Runs great |
Ran DeepSeek-R1-Distill 8B on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →