Can the NVIDIA RTX 3080 10GB run Phi-4 14B?

Yes, with heavy quantization
QuantQ3_K_MNoticeably degraded
Memory9.5 GBof 10 GB
Speed~63tokens/s

Only just. Phi-4 14B fits on the NVIDIA RTX 3080 10GB at Q3_K_M, which costs noticeable quality. Expect about 63 tokens/second. A card with more memory is a better experience.

Try other context lengths in the calculator →
Run it in the cloud

Want full quality? Run Phi-4 14B on a bigger rented GPU.

Rent a cloud GPU by the hour. No upfront cost, cancel any time.

RunPodOn-demand GPUs with ready-made templates for Ollama and vLLM.Rent a GPU on RunPod → Vast.aiA marketplace of rentable GPUs, from RTX cards to H100s.Rent a GPU on Vast.ai →

Memory needed by quantization

At 8,192 tokens of context.

QuantQualityMemoryFits?Speed
FP16Full quality31.7 GBToo big—
Q8_0Near-lossless17.9 GBToo big—
Q6_KExcellent14.3 GBToo big—
Q5_K_MVery good12.7 GBToo big—
Q4_K_MGood, most popular11.2 GBToo big—
Q3_K_MNoticeably degraded9.5 GBFits~63 tok/s
Q2_KHeavily degraded7.8 GBFits~83 tok/s

How to run Phi-4 14B on the NVIDIA RTX 3080 10GB

Ollama's default phi4:14b download is Q4_K_M, which needs about 11.2 GB, more than the 10 GB available. Download the Q3_K_M GGUF instead (LM Studio lists quants per model), or try a smaller context length.

GPUs that run Phi-4 14B comfortably

Check NVIDIA RTX 3060 12GB prices →

Models that run well on the NVIDIA RTX 3080 10GB