Youtu-VL-4B-Instruct

tencent/Youtu-VL-4B-Instruct

Image Text to Text5.3B parameterstransformersLicense: other
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
1,485
Total downloads
12.4K
Gained 7D
+684(increase)
6.1%(up) vs baseline
Gained 30D
—
Likes
162
+1 in 7D
Rank · tracked models
#28,099
1374(down 1374 places)this week
Parameters
5.3B
Last source update
Feb 10, 2026
Momentum
79.2
  • Youtu-VL-4B-Instruct gained 684 downloads during the last seven tracked days.
  • It moved from #2348 to #2476 among tracked Image Text to Text models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Youtu-VL-4B-Instruct is a image text to text model published by tencent. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 4, 2026.

Published
Jan 23, 2026
Last updated
Feb 10, 2026
Library
transformers
License
other
Task
Image Text to Text
Parameters
5,340,551,024
Spaces
—
Derivative models
—
Velocity 7D/day
98
transformerssafetensorsyoutu_vltext-generationimage-text-to-textconversationalcustom_codearxiv:2601.19798arxiv:2512.24618license:otherregion:us

Similar models

Models similar to Youtu-VL-4B-Instruct
ModelDL 30D
NV-Reason-CTnvidia2,613
Sa2VA-Qwen3-VL-4B-SAM3ByteDance799
chandra-ocr-2datalab-to2.1M
Qwen3.8-Flash-Next-4bit-pagedGreenBitAI1,067
gemma-3n-E2B-itgoogle176.2K
gemma-3n-E2B-it-unsloth-bnb-4bitunsloth3,270
tencent/Youtu-VL-4B-Instruct — Downloads, Growth & Stats | OpenModelStats