Playground/Phi-3 Vision
🔭

Phi-3 Vision

by microsoftđŸ‘ī¸ Vision & OCR

Microsoft's compact multimodal model. Understands images and answers complex questions with impressive efficiency.

VisionMultimodalMicrosoftEfficient
19.8k
Likes
0.9M
Runs
4.5
Rating
Demo Mode: Streaming output is simulated for demonstration. Click "Run" on the prompt tab to see how this space works.
0 chars
Output
🔭
Ready to run
Enter a prompt and click Run
Parameters
0.7
PreciseCreative
512
Space Info
Modelphi-3-vision
FrameworkGradio
LicenseMIT
Avg Latency2.4s