Phi-3.5-vision-instruct

microsoft/Phi-3.5-vision-instruct

Image Text to Text4.1B parameterstransformersLicense: mit
Tracked by OpenModelStats since September 6, 2026View on Hugging Face ↗
Downloads 30D
775.4K
Total downloads
20.5M
Gained 7D
+185.1K(increase)
0.9%(up) vs baseline
Gained 30D
—
Likes
739
+1 in 7D
Rank · tracked models
#499
7(down 7 places)this week
Parameters
4.1B
Last source update
Dec 10, 2025
Momentum
84.7
  • Phi-3.5-vision-instruct gained 185.1K downloads during the last seven tracked days.
  • It moved from #84 to #87 among tracked Image Text to Text models this week.

Downloads over time

Daily gain between consecutive observations

Likes over time

Rank among tracked models

Lower is better

Overview

Phi-3.5-vision-instruct is a image text to text model published by microsoft. OpenModelStats has tracked the model since Sep 6, 2026, most recently observing it Oct 6, 2026.

Published
Aug 16, 2024
Last updated
Dec 10, 2025
Library
transformers
License
mit
Task
Image Text to Text
Parameters
4,146,621,440
Spaces
—
Derivative models
1
Velocity 7D/day
26.4K
transformerssafetensorsphi3_vtext-generationnlpcodevisionimage-text-to-textconversationalcustom_codemultilingualarxiv:2404.14219

Model family

Based on base-model relationships reported by the source's metadata.

Derivative models

Similar models

Models similar to Phi-3.5-vision-instruct
ModelDL 30D
InternVL2-4BOpenGVLab14.9K
Mini-InternVL-Chat-4B-V1-5OpenGVLab235
Mini-InternVL2-4B-DA-MedicalOpenGVLab215
Ovis1.6-Llama3.2-3BATH-MaaS8,594
POINTS-Readertencent314
Qwen3.6-35B-A3B-int2-mixed-CT-AutoRoundIntel121
microsoft/Phi-3.5-vision-instruct — Downloads, Growth & Stats | OpenModelStats