GeekRadar / The comparison desk
COMPARE.
AI models
microsoft

phi-3-small 7.4B

AI model Released

Open weights
Yes*

Capability & preference

General capability · ECI

A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.

phi-3-small 7.4B 116.6* phi-3-small 7.4B · 95% interval 111.0–122.1

Run it locally

Inference · memory estimate

phi-3-small 7.4B

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Open weights
Yes*

System configuration

Detailed specifications

Specifications · 4 fields
Access model
Open weights (unrestricted)*
Open weights
Yes*
Organization
Microsoft*
Organization country
United States of America*

* Provisional data