Skip to content
localmodel.run

Text model · phi

Phi-4 14B requirements

phi family · 14B params · released Dec 2024 · 7.3M Ollama pulls · LMArena Elo 1256. Minimum to run at Q4_K_M: Nvidia GeForce RTX 3060 (12GB).

LicenseMIT· Commercial OK↓ 714.1K/mo♥ 2.3Kon HuggingFace
Q4_K_M
9.05 GB
Q8_0
15.58 GB
Total @ Q4 (4k)
~10.8 GB
Context
16 k

Quantization sizes

GGUF quantson disk
QuantizationSize on disk
Q2_K5.9 GB est
Q3_K_M6.8 GB est
Q4_K_M (default)9.05 GB
Q5_K_M10 GB est
Q6_K11.5 GB est
Q8_015.58 GB
FP1628 GB est

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

Ollama
$ ollama run phi4:14b
llama.cpp
$ llama-cli -hf bartowski/phi-4-GGUF:Q4_K_M
LM Studio
$ lms get bartowski/phi-4-GGUF

Which devices can run Phi-4 14B?

FAQ

How much VRAM or RAM does Phi-4 14B need?

At Q4_K_M, Phi-4 14B needs about 10.8 GB (weights ~9.05 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~17.3 GB.

Can Phi-4 14B run on a laptop?

Phi-4 14B is large; you need a 24 GB+ GPU or a 32-48 GB Mac at Q4_K_M.

Can I use Phi-4 14B commercially?

Yes. Phi-4 14B is licensed MIT, which permits commercial use.

Released December 12, 2024 by Microsoft. Strong math and reasoning. Default context 16K. Ollama shows 9.1GB; bartowski HF gives precise 9.05GB Q4_K_M and 15.58GB Q8_0.

Sources

Memory figures are estimates. See methodology.