GroundAnything

GroundingPI/GroundAnything

Image Text to Text4.8B parameterstransformersLicense: other
Tracked by OpenModelStats since September 30, 2026View on Hugging Face ↗
Downloads 30D
706
Total downloads
706
Gained 7D
—
Gained 30D
—
Likes
21
Rank · tracked models
#41,507
500(up 500 places)this week
Parameters
4.8B
Last source update
Oct 14, 2026
  • It moved from #4029 to #3995 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

GroundAnything is a image text to text model published by GroundingPI. OpenModelStats has tracked the model since Sep 30, 2026, most recently observing it Oct 27, 2026.

Published
Sep 30, 2026
Last updated
Oct 14, 2026
Library
transformers
License
other
Task
Image Text to Text
Parameters
4,843,669,504
Spaces
—
Derivative models
—
Velocity 7D/day
—
transformerssafetensorsgroundinganythingtext-generationvisual-groundingobject-detectionreferring-expression-comprehensionpointingocrdocument-layoutcustom-codediffusion-language-model

Similar models

Models similar to GroundAnything
ModelDL 30D
GroundingPIGroundingPI1,008
GroundAnything-VLMGroundingPI611
Molmo2-ERallenai24.5K
Molmo2-4Ballenai21K
MolmoWeb-4Ballenai2,170
Hulu-Med-4BZJU-AI4H1,895
GroundingPI/GroundAnything — Downloads, Growth & Stats | OpenModelStats