LocateAnything-3B
nvidia/LocateAnything-3B
- kind
- original
- quant
- bf16 (16-bit)
- family
- misc
- modality
- image-text-to-text
- root model
- Qwen/Qwen2.5-3B-Instruct
- provider
- nvidia
- license
- other
- language
- en
- context
- —
- library
- transformers
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 1,249,399
- likes
- 2,794
- created
- —
- last modified
- 2026-06-12T10:51:04+00:00 (2026)
- huggingface
- https://huggingface.co/nvidia/LocateAnything-3B
- tags
- transformerssafetensorslocateanythingfeature-extractionnvidiaeaglevisionobject-detectiongroundingarxiv:2605.27365image-text-to-textconversationalcustom_codeenarxiv:2504.07491arxiv:2109.10852arxiv:2510.12798arxiv:2303.05499arxiv:1405.0312arxiv:1908.03195arxiv:2504.07981base_model:Qwen/Qwen2.5-3B-Instructbase_model:finetune:Qwen/Qwen2.5-3B-Instructlicense:other
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.