Can I run this LLM?
Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Llama 3.3 70B Instruct?
Llama · Llama 3.3 Community · estimated for a 144.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Llama 3.3 70B Instruct at Q8_0 · 75.0 GB · 42–63 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 26.4 GB | 96–144 tok/s | Runs great |
| Q3_K_M | 34.3 GB | 80–119 tok/s | Runs great |
| Q4_K_M | 42.5 GB | 67–101 tok/s | Runs great |
| Q5_K_M | 50.0 GB | 59–89 tok/s | Runs great |
| Q6_K | 57.9 GB | 52–79 tok/s | Runs great |
| Q8_0 | 75.0 GB | 42–63 tok/s | Runs great |
| FP16 | 141.1 GB | 12–17 tok/s | Tight / slow |
Open the full calculator →Everything a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) runsLlama 3.3 70B Instruct on other machinesWhat to buy to run it →
Ran Llama 3.3 70B Instruct on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →