Can the NVIDIA RTX 4070 run Phi-4 14B?
Yes
QuantQ4_K_MGood, most popular
Memory11.2 GBof 12 GB
Speed~34tokens/s
Yes. The NVIDIA RTX 4070 can run Phi-4 14B fully in VRAM at Q4_K_M (good, most popular), using about 11.2 GB of the 12 GB available, at roughly 34 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 | Too big | — |
| Q8_0 | Near-lossless | 17.9 GB | Too big | — |
| Q6_K | Excellent | 14.3 GB | Too big | — |
| Q5_K_M | Very good | 12.7 GB | Too big | — |
| Q4_K_M | Good, most popular | 11.2 GB | Fits | ~34 tok/s |
| Q3_K_M | Noticeably degraded | 9.5 GB | Fits | ~42 tok/s |
| Q2_K | Heavily degraded | 7.8 GB | Fits | ~55 tok/s |
How to run Phi-4 14B on the NVIDIA RTX 4070
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). That is also the best quant that fits.
GPUs that run Phi-4 14B comfortably
- NVIDIA RTX 3060 12GB
- NVIDIA RTX 5070 (12 GB)
- NVIDIA RTX 4060 Ti 16GB
- NVIDIA RTX 5060 Ti 16GB
- AMD Radeon RX 7800 XT (16 GB)
Models that run well on the NVIDIA RTX 4070
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.