Phi 4 Models — Hardware Requirements

7 Phi 4 models from Microsoft and the community, from the smallest that runs in 1.6 GB of VRAM up to 14.7B parameters. Every row links to full quantization tables and GPU compatibility.

All Phi 4 Models by Size

ModelParamsContext
Phi 4 Mini Instruct3.8B131K
Phi 4 Mini Reasoning3.8B131K
Phi 4 Mini Flash Reasoning3.9B262K
Phi 414.7B16K
Phi 4 Reasoning Plus14.7B33K
Phi 4 Reasoning14.7B33K
Phi 4 Quantized.w8a814.7B16K

How Phi 4 Compares — Benchmark Rating

Phi 4 is the highest-rated Phi 4 model with an overall benchmark rating of 53.5/100 — #30 among 75 open models. The top proprietary model, GPT 5.5, scores 88.8. Click a model to see its full benchmark breakdown.

GPT 5.5 · proprietary88.8
Claude Opus 4.7 · proprietary87.6
Claude Fable 5 · proprietary86.6
GPT 5.4 · proprietary86.6
Claude Opus 4.8 · proprietary84.4
Phi 453.5
Composite of normalized public benchmark scores (methodology) · Phi 4 · other models

Frequently Asked Questions

How much VRAM do I need to run a Phi 4 model?
The smallest Phi 4 model, Phi 4 Mini Reasoning, runs from 1.6 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
Which Phi 4 models can I run on a 16 GB GPU?
7 of 7 Phi 4 models fit in 16 GB of VRAM at some quantization, including Phi 4 Mini Instruct, Phi 4, Phi 4 Mini Reasoning.
What is the most popular Phi 4 model to run locally?
Phi 4 Mini Instruct is the most downloaded Phi 4 model in local-friendly quantized formats. It runs from 2.2 GB of VRAM.
How do Phi 4 models score on benchmarks?
Phi 4 leads the family with an overall benchmark rating of 53.5/100, ranking #30 among 75 open models, while the top proprietary model, GPT 5.5, scores 88.8. See the comparison chart above for the full standings.