Basic information
Model repository: nv-community/LocateAnything-3B
Organization: nv-community
Tasks: image-text-to-text
Architecture and runtime
Model type: locateanything
Architecture: LocateAnythingForConditionalGeneration
Libraries: pytorch, transformer, safetensors
Base models: Qwen/Qwen2.5-3B-Instruct
Current revision: master
License and update history
License: nvidia-license
Created: 2026-05-28
Last updated: 2026-06-13
Hardware requirements
Not filled in locally.
Download links
Not filled in locally.
Basic usage example
Not filled in locally.