Qianfan-VL-3B

baidu/Qianfan-VL-3B

Image Text to Text3.7B parameterstransformersLicense: other
Tracked by OpenModelStats since September 4, 2026View on Hugging Face ↗
Downloads 30D
190
Total downloads
2,535
Gained 7D
+40(increase)
1.7%(up) vs baseline
Gained 30D
—
Likes
30
+0 in 7D
Rank · tracked models
#51,315
267(down 267 places)this week
Parameters
3.7B
Last source update
Sep 19, 2025
Momentum
31.2
  • Qianfan-VL-3B gained 40 downloads during the last seven tracked days.
  • It moved from #4726 to #4735 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

Qianfan-VL-3B is a image text to text model published by baidu. OpenModelStats has tracked the model since Sep 4, 2026, most recently observing it Oct 4, 2026.

Published
Sep 16, 2025
Last updated
Sep 19, 2025
Library
transformers
License
other
Task
Image Text to Text
Parameters
3,713,711,104
Spaces
0
Derivative models
—
Velocity 7D/day
6
transformerssafetensorsqianfanvl_chatfeature-extractionmultimodalimage-text-to-textconversationalcustom_codeenzhlicense:otherregion:us

Similar models

Models similar to Qianfan-VL-3B
ModelDL 30D
Qianfan-VL-3Bcoblack641
InternVL2_5-4B-MPOOpenGVLab46.4K
InternVL2_5-4BOpenGVLab8,425
Vintern-3B-R-beta5CD-AI765
Vintern-3B-beta5CD-AI570
blip2-opt-2.7bSalesforce656.9K
baidu/Qianfan-VL-3B — Downloads, Growth & Stats | OpenModelStats