Mage-VL

microsoft/Mage-VL

Image Text to Text4.7B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since September 4, 2026View on Hugging Face ↗
Downloads 30D
10.5K
Total downloads
522.6K
Gained 7D
+2,354(increase)
0.5%(up) vs baseline
Gained 30D
—
Likes
416
+7 in 7D
Rank · tracked models
#7,866
202(down 202 places)this week
Parameters
4.7B
Last source update
Aug 10, 2026
Momentum
78.2
  • Mage-VL gained 2,354 downloads during the last seven tracked days.
  • It moved from #922 to #936 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

Mage-VL is a image text to text model published by microsoft. OpenModelStats has tracked the model since Sep 4, 2026, most recently observing it Oct 4, 2026.

Published
Jul 25, 2026
Last updated
Aug 10, 2026
Library
transformers
License
apache-2.0
Task
Image Text to Text
Parameters
4,741,793,792
Spaces
—
Derivative models
3
Velocity 7D/day
336
transformerssafetensorsmage_vlimage-text-to-textmultimodalvision-language-modelmage-vlvideo-understandingstreamingconversationalcustom_codearxiv:2607.24904

Model family

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

Similar models

Models similar to Mage-VL
ModelDL 30D
Mage-VL-8bitmlx-community233
LLaVA-OneVision-1.5-4B-Instructlmms-lab1,166
Qianfan-OCRbaidu220.5K
QianfanOCRbairongz1,046
Qwen3.5-4B-AWQ-BF16-INT8cyankiwi363
Qwen3.5-4B-AWQ-BF16-INT4cyankiwi261
microsoft/Mage-VL — Downloads, Growth & Stats | OpenModelStats