Can I run this LLM?
Can a NVIDIA H200 (141GB) run Phi-4 14B?
Phi · MIT · estimated for a 141.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Phi-4 14B at FP16 · 29.3 GB · 89–134 tok/s on a NVIDIA H200 (141GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 5.6 GB | 220–330 tok/s | Runs great |
| Q3_K_M | 7.2 GB | 200–301 tok/s | Runs great |
| Q4_K_M | 8.9 GB | 183–274 tok/s | Runs great |
| Q5_K_M | 10.4 GB | 170–254 tok/s | Runs great |
| Q6_K | 12.0 GB | 157–236 tok/s | Runs great |
| Q8_0 | 15.6 GB | 136–204 tok/s | Runs great |
| FP16 | 29.3 GB | 89–134 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA H200 (141GB) runsPhi-4 14B on other machinesWhat to buy to run it →
Ran Phi-4 14B on a NVIDIA H200 (141GB)? Add your real numbers →