LocateAnything-3B

nvidia/LocateAnything-3B

Image Text to Text3.8B parameterstransformersLicense: other
Tracked by OpenModelStats since September 6, 2026View on Hugging Face ↗
Downloads 30D
163.5K
Total downloads
2.3M
Gained 7D
+10.3K(increase)
0.5%(up) vs baseline
Gained 30D
—
Likes
3,093
+22 in 7D
Rank · tracked models
#1,997
295(up 295 places)this week
Parameters
3.8B
Last source update
Jun 12, 2026
Momentum
82.2
  • LocateAnything-3B gained 10.3K downloads during the last seven tracked days.
  • It moved from #349 to #310 among tracked Image Text to Text models this week.
  • The model earned 22 new likes over the last seven tracked days.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

LocateAnything-3B is a image text to text model published by nvidia. OpenModelStats has tracked the model since Sep 6, 2026, most recently observing it Oct 6, 2026.

Published
Mar 2, 2026
Last updated
Jun 12, 2026
Library
transformers
License
other
Task
Image Text to Text
Parameters
3,830,665,968
Spaces
—
Derivative models
6
Velocity 7D/day
1,465
transformerssafetensorslocateanythingfeature-extractionnvidiaeaglevisionobject-detectiongroundingarxiv:2605.27365image-text-to-textconversational

Model family

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

Similar models

nvidia/LocateAnything-3B — Downloads, Growth & Stats | OpenModelStats