WeVisOne-VL-4B

litert-community/WeVisOne-VL-4B

Image Text to Textlitert-lmLicense: apache-2.0
Tracked by OpenModelStats since November 10, 2026View on Hugging Face ↗
Downloads 30D
121
Total downloads
121
Gained 7D
—
Gained 30D
—
Likes
0
Rank · tracked models
#73,837
385(down 385 places)this week
Parameters
—
Last source update
Nov 12, 2026
  • It moved from #6420 to #6473 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

WeVisOne-VL-4B is a image text to text model published by litert-community. OpenModelStats has tracked the model since Nov 10, 2026, most recently observing it Nov 12, 2026.

Published
Nov 10, 2026
Last updated
Nov 12, 2026
Library
litert-lm
License
apache-2.0
Task
Image Text to Text
Parameters
—
Spaces
—
Derivative models
—
Velocity 7D/day
—
litert-lmlitertlitertlmon-devicevision-languageobject-detectionreferring-expression-comprehensionobject-countingpoint-groundingocrimage-text-to-textbase_model:tencent/WeVisOne-VL-4B

Publisher

litert-communityView publisher statistics →

Derived from tencent/WeVisOne-VL-4B (reported by the source; parent not yet tracked).

Similar models

Models similar to WeVisOne-VL-4B
ModelDL 30D
Florence-2-basemicrosoft15M
Qwen3-VL-8B-InstructQwen7.1M
Qwen3.8-27BQwen7M
Qwen3.8-Flash-Next-GSQ-RCO-GGUFISTA-DASLab6.9M
gemma-4-31B-itgoogle6.6M
GLM-5.3-Flashzai-org6.4M
litert-community/WeVisOne-VL-4B — Downloads, Growth & Stats | OpenModelStats