nvidia/LocateAnything-3B
image-text-to-text model by nvidia
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
LocateAnything is a vision-language model for fast and high-quality visual grounding, enabling precise object localization, dense detection, and point-based localization across diverse domains in both Enterprise Intelligence and Physical AI. The model adopts a generalist design, supporting tasks such as referring expression grounding, multi-object detection, GUI element grounding, and text localization, with strong performance in complex and cluttered scenes. Its core innovation, Parallel Box Decoding (PBD), predicts complete bounding box coordinates in a single parallel step rather than autoregressive token-by-token decoding, improving efficiency while preserving geometric consistency. This enables up to 2.5× higher throughput compared to prior approaches. The model is trained on a large-scale multi-domain dataset (12M images, 138M+ queries, 785M bounding boxes) spanning natural scenes, robotics, driving, GUI interaction, and document understanding. It serves as a foundation for generalist multimodal perception and has been integrated into NVIDIA’s frontier production-grade vision-language models, such as Nemotron 3 Nano Omni, supporting…
Read the full model card ↗ · Preview checked 2026-10-28T03:28:53.177Z
Inside the original model card — Document outline
- LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
- 🔗 Quick Links
- Model Overview
- Description:
- Demo Videos
- License/Terms of Use:
- Deployment Geography:
- Use Case:
- Release Date [Insert the expected release date below]:
- References(s):
- Model Architecture:
- Input(s):
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
nvidia/LocateAnything-3B is a image-text-to-text model repository published by nvidia on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 377,461
- Cumulative likes
- 3,157
- Hugging Face trending score
- 26
- Reported safetensors parameters
- 3,830,665,968
- Architecture
- LocateAnythingForConditionalGeneration
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-03-02T20:05:49.000Z
- Last modified
- 2026-06-12T10:51:04.000Z
Compatibility and lineage
Reported languages: en
Reported base models: Qwen/Qwen2.5-3B-Instruct
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:50:33.901Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.