Rent a GPU

Can the NVIDIA RTX 5080 run Phi-4 Mini 3.8B?

RTX 5080 × Phi-4 Mini 3.8B8K context
YesRuns fully on the GPU
Memory at FP169.4 GB of 16 GB
Weights 7.7 GBKV cache 1.1 GBRuntime 0.6 GB
QuantFP16Full quality
Speed~75tokens per second
Max context56Ktokens 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 5080 can run Phi-4 Mini 3.8B fully in VRAM at FP16 (full quality), using about 9.4 GB of the 16 GB available, at roughly 75 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Phi-4 Mini 3.8B:

ollama run phi4-mini:3.8b

Ollama's default download is Q4_K_M (about 4 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 5080

Run it in the cloud

No NVIDIA RTX 5080? Run Phi-4 Mini 3.8B 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 16 GB the NVIDIA RTX 5080 can use.

QuantQualityMemoryFits?Speed
FP16Full quality9.4 GBFits~75 tok/s
Q8_0Near-lossless5.8 GBFits~141 tok/s
Q6_KExcellent4.8 GBFits~183 tok/s
Q5_K_MVery good4.4 GBFits~211 tok/s
Q4_K_MGood, most popular4 GBFits~247 tok/s
Q3_K_MNoticeably degraded3.6 GBFits~307 tok/s
Q2_KHeavily degraded3.1 GBFits~400 tok/s

Measured speed from real RTX 5080 owners

Tokens per second that people measured on their own NVIDIA RTX 5080, next to our estimate.

No one has measured Phi-4 Mini 3.8B on the NVIDIA RTX 5080 yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX 5080? Add your real speed

One command times Phi-4 Mini 3.8B 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-mini:3.8b

Windows (PowerShell)

$env:GPUFIT_MODEL="phi4-mini:3.8b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Phi-4 Mini 3.8B comfortably

Models that run well on the NVIDIA RTX 5080

Frequently asked questions

Can NVIDIA RTX 5080 run Phi-4 Mini 3.8B?

Yes. The NVIDIA RTX 5080 can run Phi-4 Mini 3.8B fully in VRAM at FP16 (full quality), using about 9.4 GB of the 16 GB available, at roughly 75 tokens/second.

How much VRAM does Phi-4 Mini 3.8B need?

About 4 GB at Q4_K_M with 8,192 tokens of context, and about 9.4 GB at full FP16 precision.

How fast is Phi-4 Mini 3.8B on the NVIDIA RTX 5080?

Roughly 75 tokens per second at FP16, estimated from the NVIDIA RTX 5080's 960 GB/s memory bandwidth.