Can the NVIDIA RTX 5090 run Phi-4 14B?
Yes
QuantFP16Full quality
Memory31.7 GBof 32 GB
Speed~37tokens/s
Yes. The NVIDIA RTX 5090 can run Phi-4 14B fully in VRAM at FP16 (full quality), using about 31.7 GB of the 32 GB available, at roughly 37 tokens/second.
Try other context lengths in the calculator →Memory needed by quantization
At 8,192 tokens of context.
| Quant | Quality | Memory | Fits? | Speed |
|---|---|---|---|---|
| FP16 | Full quality | 31.7 GB | Fits | ~37 tok/s |
| Q8_0 | Near-lossless | 17.9 GB | Fits | ~69 tok/s |
| Q6_K | Excellent | 14.3 GB | Fits | ~89 tok/s |
| Q5_K_M | Very good | 12.7 GB | Fits | ~103 tok/s |
| Q4_K_M | Good, most popular | 11.2 GB | Fits | ~121 tok/s |
| Q3_K_M | Noticeably degraded | 9.5 GB | Fits | ~150 tok/s |
| Q2_K | Heavily degraded | 7.8 GB | Fits | ~195 tok/s |
How to run Phi-4 14B on the NVIDIA RTX 5090
With Ollama installed, one command downloads and starts it:
ollama run phi4:14bOllama's default download is Q4_K_M (about 11.2 GB here). You have room for FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.
GPUs that run Phi-4 14B comfortably
- NVIDIA RTX 3060 12GB
- NVIDIA RTX 4070 (12 GB)
- NVIDIA RTX 5070 (12 GB)
- NVIDIA RTX 4060 Ti 16GB
- NVIDIA RTX 5060 Ti 16GB
Models that run well on the NVIDIA RTX 5090
Run it in the cloud
Don't want to buy hardware? Run Phi-4 14B on a rented GPU today.
Rent a cloud GPU by the hour. No upfront cost, cancel any time.