Can I run this LLM?
Can a NVIDIA RTX 6000 Ada (48GB) run Phi-4 14B?
Phi · MIT · estimated for a 48.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Phi-4 14B at FP16 · 29.3 GB · 22–33 tok/s on a NVIDIA RTX 6000 Ada (48GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 5.6 GB | 85–127 tok/s | Runs great |
| Q3_K_M | 7.2 GB | 71–107 tok/s | Runs great |
| Q4_K_M | 8.9 GB | 61–91 tok/s | Runs great |
| Q5_K_M | 10.4 GB | 54–81 tok/s | Runs great |
| Q6_K | 12.0 GB | 48–72 tok/s | Runs great |
| Q8_0 | 15.6 GB | 39–58 tok/s | Runs great |
| FP16 | 29.3 GB | 22–33 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA RTX 6000 Ada (48GB) runsPhi-4 14B on other machinesWhat to buy to run it →
Ran Phi-4 14B on a NVIDIA RTX 6000 Ada (48GB)? Add your real numbers →