Can I run this LLM?
Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Llama 3.2 3B?
Llama · Llama 3.2 Community · estimated for a 144.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Llama 3.2 3B at FP16 · 6.4 GB · 216–324 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q4_K_M | 1.9 GB | 295–442 tok/s | Runs great |
| Q5_K_M | 2.3 GB | 287–430 tok/s | Runs great |
| Q6_K | 2.6 GB | 279–418 tok/s | Runs great |
| Q8_0 | 3.4 GB | 263–395 tok/s | Runs great |
| FP16 | 6.4 GB | 216–324 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) runsLlama 3.2 3B on other machinesWhat to buy to run it →
Ran Llama 3.2 3B on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →