Can I run this LLM?
Can a NVIDIA H200 (141GB) run Gemma 3 27B?
Gemma · Gemma · estimated for a 141.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Gemma 3 27B at FP16 · 54.0 GB · 54–81 tok/s on a NVIDIA H200 (141GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 10.5 GB | 159–239 tok/s | Runs great |
| Q3_K_M | 13.4 GB | 141–211 tok/s | Runs great |
| Q4_K_M | 16.6 GB | 125–188 tok/s | Runs great |
| Q5_K_M | 19.3 GB | 114–171 tok/s | Runs great |
| Q6_K | 22.2 GB | 105–157 tok/s | Runs great |
| Q8_0 | 28.7 GB | 88–131 tok/s | Runs great |
| FP16 | 54.0 GB | 54–81 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA H200 (141GB) runsGemma 3 27B on other machinesWhat to buy to run it →
Ran Gemma 3 27B on a NVIDIA H200 (141GB)? Add your real numbers →