Can I run this LLM?
Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Gemma 4 31B?
Gemma · Apache 2.0 · estimated for a 144.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Gemma 4 31B at FP16 · 61.4 GB · 50–75 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 14.7 GB | 140–211 tok/s | Runs great |
| Q4_K_M | 18.3 GB | 123–185 tok/s | Runs great |
| Q5_K_M | 21.7 GB | 111–166 tok/s | Runs great |
| Q6_K | 25.2 GB | 100–150 tok/s | Runs great |
| Q8_0 | 32.6 GB | 83–124 tok/s | Runs great |
| FP16 | 61.4 GB | 50–75 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) runsGemma 4 31B on other machinesWhat to buy to run it →
Ran Gemma 4 31B on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →