Rent a GPU

Can the Intel Arc B580 run Phi-4 Reasoning 14B?

Intel Arc B580 × Phi-4 Reasoning 14B8K context
YesRuns fully on the GPU
Memory at Q4_K_M11.2 GB of 12 GB
Weights 8.9 GBKV cache 1.7 GBRuntime 0.6 GB
QuantQ4_K_MGood, most popular
Speed~31tokens per second
Max context11Ktokens that fit at Q4_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

Yes. The Intel Arc B580 can run Phi-4 Reasoning 14B fully in VRAM at Q4_K_M (good, most popular), using about 11.2 GB of the 12 GB available, at roughly 31 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). That is also the best quant that fits.

New to this? Step-by-step setup for the Intel Arc B580

Run it in the cloud

No Intel Arc B580? 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 12 GB the Intel Arc B580 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 GBFits~31 tok/s
Q3_K_MNoticeably degraded9.5 GBFits~38 tok/s
Q2_KHeavily degraded7.8 GBFits~50 tok/s

Measured speed from real Intel Arc B580 owners

Tokens per second that people measured on their own Intel Arc B580, next to our estimate.

No one has measured Phi-4 Reasoning 14B on the Intel Arc B580 yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Intel Arc B580? 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 Intel Arc B580

Frequently asked questions

Can Intel Arc B580 run Phi-4 Reasoning 14B?

Yes. The Intel Arc B580 can run Phi-4 Reasoning 14B fully in VRAM at Q4_K_M (good, most popular), using about 11.2 GB of the 12 GB available, at roughly 31 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 Intel Arc B580?

Roughly 31 tokens per second at Q4_K_M, estimated from the Intel Arc B580's 456 GB/s memory bandwidth.