🤖 image-text-to-text

LocateAnything-3B

nvidia/LocateAnything-3B

Get AI Model →
407.8K
Downloads
❤️
2.4K
Likes
🏷️
25
Tags
📦
transformers
Library
Model Details
Full Model IDnvidia/LocateAnything-3B
Pipeline / Taskimage-text-to-text
Librarytransformers
Downloads (all-time)407.8K
Likes2.4K
Last Modified6/12/2026
Author / Orgnvidia
PrivateNo — public
⚡ Quick Usage (Python)

Using the 🤗 Transformers library. Install with pip install transformers

from transformers import pipeline

# Load the model
pipe = pipeline("image-text-to-text", model="nvidia/LocateAnything-3B")

# Run inference
result = pipe("Your input here")
print(result)
🏷️ 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:otherregion:us
More image-text-to-text Models
See all →
gemma-4-26B-A4B-it

google/gemma-4-26B-A4B-it

13.1M❤️ 1.2K
Get AI Model →
gemma-4-31B-it

google/gemma-4-31B-it

11.2M❤️ 3.1K
Get AI Model →
Qwen3.5-9B

Qwen/Qwen3.5-9B

9.8M❤️ 1.6K
Get AI Model →
🚀 Use This Model

Access model files, inference API, and full documentation on Hugging Face.

Open on Hugging Face →Browse Model Files ↗← Browse All Models
🤖 Task: image-text-to-text

This model is designed for the image-text-to-text task. Explore more models for this use case.

All image-text-to-text Models →
📊 Popularity
Downloads407.8K
❤️ Community Likes2.4K
🛠️ Requirements
  • Install: pip install transformers
  • Python 3.8+ recommended for Transformers.
  • GPU (CUDA) speeds up inference significantly.
  • Use model.half() for fp16 on limited VRAM.
👋 Need help with code?