InternVL3_5-4B-HF

OpenGVLab/InternVL3_5-4B-HF

Image Text to Text4.7B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since September 8, 2026View on Hugging Face ↗
Downloads 30D
15.4K
Total downloads
94.5K
Gained 7D
+4,950(increase)
6.0%(up) vs baseline
Gained 30D
—
Likes
6
+1 in 7D
Rank · tracked models
#6,637
136(up 136 places)this week
Parameters
4.7B
Last source update
Sep 8, 2025
Momentum
88.2
  • InternVL3_5-4B-HF gained 4,950 downloads during the last seven tracked days.
  • It moved from #839 to #824 among tracked Image Text to Text models this week.

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Overview

InternVL3_5-4B-HF is a image text to text model published by OpenGVLab. OpenModelStats has tracked the model since Sep 8, 2026, most recently observing it 6h ago.

Published
Aug 29, 2025
Last updated
Sep 8, 2025
Library
transformers
License
apache-2.0
Task
Image Text to Text
Parameters
4,732,489,216
Spaces
—
Derivative models
3
Velocity 7D/day
707
transformerssafetensorsinternvlimage-text-to-textcustom_codeconversationalmultilingualdataset:OpenGVLab/MMPR-v1.2dataset:OpenGVLab/MMPR-Tinyarxiv:2312.14238arxiv:2404.16821arxiv:2412.05271

Publisher

OpenGVLabView publisher statistics →

Derived from OpenGVLab/InternVL3_5-4B-MPO (reported by the source; parent not yet tracked).

Model family

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

Similar models

Models similar to InternVL3_5-4B-HF
ModelDL 30D
InternVL3_5-4BOpenGVLab19.4K
InternVL3_5-4B-InstructOpenGVLab716
InternVL3_5-4B-PretrainedOpenGVLab504
Qianfan-OCRbaidu86.6K
QianfanOCRbairongz916
LLaVA-OneVision-1.5-4B-Instructlmms-lab1,258
OpenGVLab/InternVL3_5-4B-HF — Downloads, Growth & Stats | OpenModelStats