Rent a GPU

Can the NVIDIA RTX 5090 run Phi-4 Reasoning 14B?

RTX 5090 × Phi-4 Reasoning 14B8K context
YesRuns fully on the GPU
Memory at FP1631.7 GB of 32 GB
Weights 29.4 GBKV cache 1.7 GBRuntime 0.6 GB
QuantFP16Full quality
Speed~37tokens per second
Max context8Ktokens that fit at FP16
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Yes. The NVIDIA RTX 5090 can run Phi-4 Reasoning 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

Run it with Ollama

With Ollama installed, one command downloads and starts Phi-4 Reasoning 14B:

ollama run phi4-reasoning:14b

Ollama'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.

New to this? Step-by-step setup for the RTX 5090

Run it in the cloud

No NVIDIA RTX 5090? Run Phi-4 Reasoning 14B in the cloud.

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

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 32 GB the NVIDIA RTX 5090 can use.

QuantQualityMemoryFits?Speed
FP16Full quality31.7 GBFits~37 tok/s
Q8_0Near-lossless17.9 GBFits~69 tok/s
Q6_KExcellent14.3 GBFits~89 tok/s
Q5_K_MVery good12.7 GBFits~103 tok/s
Q4_K_MGood, most popular11.2 GBFits~121 tok/s
Q3_K_MNoticeably degraded9.5 GBFits~150 tok/s
Q2_KHeavily degraded7.8 GBFits~195 tok/s

Measured speed from real RTX 5090 owners

Tokens per second that people measured on their own NVIDIA RTX 5090, next to our estimate.

No one has measured Phi-4 Reasoning 14B on the NVIDIA RTX 5090 yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX 5090? Add your real speed

One command times Phi-4 Reasoning 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-reasoning:14b

Windows (PowerShell)

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

How the benchmark works

GPUs that run Phi-4 Reasoning 14B comfortably

Models that run well on the NVIDIA RTX 5090

Frequently asked questions

Can NVIDIA RTX 5090 run Phi-4 Reasoning 14B?

Yes. The NVIDIA RTX 5090 can run Phi-4 Reasoning 14B fully in VRAM at FP16 (full quality), using about 31.7 GB of the 32 GB available, at roughly 37 tokens/second.

How much VRAM does Phi-4 Reasoning 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 Reasoning 14B on the NVIDIA RTX 5090?

Roughly 37 tokens per second at FP16, estimated from the NVIDIA RTX 5090's 1792 GB/s memory bandwidth.