Rent a GPU

Can the NVIDIA RTX 2080 Ti run Phi-4 14B?

RTX 2080 Ti × Phi-4 14B8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q3_K_M9.5 GB of 11 GB
Weights 7.2 GBKV cache 1.7 GBRuntime 0.6 GB
QuantQ3_K_MNoticeably degraded
Speed~51tokens per second
Max context15Ktokens that fit at Q3_K_M
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Only just. Phi-4 14B fits on the NVIDIA RTX 2080 Ti at Q3_K_M, which costs noticeable quality. Expect about 51 tokens/second. A card with more memory is a better experience.

Try other context lengths

Run it with Ollama

Ollama's default phi4:14b download is Q4_K_M, which needs about 11.2 GB, more than the 11 GB available. Download the Q3_K_M GGUF instead (LM Studio lists quants per model), or try a smaller context length.

New to this? Step-by-step setup for the RTX 2080 Ti

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, stop any time. Not sure whether to rent or buy? Compare the cost.

Rent a GPU on RunPodRent a GPU on Vast.ai

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 11 GB the NVIDIA RTX 2080 Ti can use.

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~51 tok/s
Q2_KHeavily degraded7.8 GBFits~67 tok/s

Measured speed from real RTX 2080 Ti owners

Tokens per second that people measured on their own NVIDIA RTX 2080 Ti, next to our estimate.

No one has measured Phi-4 14B on the NVIDIA RTX 2080 Ti yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX 2080 Ti? Add your real speed

One command times Phi-4 14B in your own Ollama, shows you exactly what it would send, and asks before sending anything. No sign-up, no personal data.

macOS and Linux

curl -fsSL https://gpufit.dev/bench.sh | sh -s -- phi4:14b

Windows (PowerShell)

$env:GPUFIT_MODEL="phi4:14b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Phi-4 14B comfortably

Check RTX 3060 12GB prices

Models that run well on the NVIDIA RTX 2080 Ti

Frequently asked questions

Can NVIDIA RTX 2080 Ti run Phi-4 14B?

Only just. Phi-4 14B fits on the NVIDIA RTX 2080 Ti at Q3_K_M, which costs noticeable quality. Expect about 51 tokens/second. A card with more memory is a better experience.

How much VRAM does Phi-4 14B need?

About 11.2 GB at Q4_K_M with 8,192 tokens of context, and about 31.7 GB at full FP16 precision.

How fast is Phi-4 14B on the NVIDIA RTX 2080 Ti?

Roughly 51 tokens per second at Q3_K_M, estimated from the NVIDIA RTX 2080 Ti's 616 GB/s memory bandwidth.