Phi-3.5-vision-instruct
microsoft/Phi-3.5-vision-instruct
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 831.2K
- Total downloadsCumulative all-time download counter reported by the source platform.
- 20.5M
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +185.1K(increase)
- 0.9%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 739
- +1 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #82 among tracked Image Text to Text models.
- #482
- 4(up 4 places)this week
- Parameters
- 4.1B
- Last source update
- Dec 10, 2025
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 84.7
- Phi-3.5-vision-instruct gained 185.1K downloads during the last seven tracked days.
- It moved from #83 to #82 among tracked Image Text to Text models this week.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
Phi-3.5-vision-instruct is a image text to text model published by microsoft. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 3, 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
Publisher
microsoftView publisher statistics →Model family
Based on base-model relationships reported by the source's metadata.
Derivative models
- VLM2Vec-Full182.7K
Similar models
| Model | DL 30D |
|---|---|
| InternVL2-4BOpenGVLab | 15.1K |
| Mini-InternVL-Chat-4B-V1-5OpenGVLab | 227 |
| Mini-InternVL2-4B-DA-MedicalOpenGVLab | 224 |
| Ovis1.6-Llama3.2-3BATH-MaaS | 8,609 |
| POINTS-Readertencent | 299 |
| Qwen3.6-35B-A3B-int2-mixed-CT-AutoRoundIntel | 117 |