Model reference · open weights
LocateAnything is an open-weight language model from nvidia, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding 🔗 Quick Links 🚀 Online Demo: LocateAnything (Hugging Face Spaces) 💻 GitHub Code: NVlabs/Eagle/Embodied 📄 Paper: arXiv:2605.27365 Model Overview Description: 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 grounding, GUI understanding, and multimodal agentic capabilities. LocateAnything is developed as part of the Eagle VLM model family. This released model is for research and development only. In addition, LocateAnything contributed to Nemotron and Cosmos as part of the Computer Use and Visual Grounding features. We give special thanks the Nemotron and Cosmos Teams for time and efforts in product integration. Demo Videos Your browser does not support the video tag. Your browser does not support the video tag. License/Terms of Use: This model is released under the NVIDIA License for non-commercial use, which permits use, reproduction, and modification for academic and non-profit research purposes only. Commercial use is not permitted, except by NVIDIA and its affiliates. Redistribution
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | nvidia |
|---|---|
| Type | Language models |
| Parameters (lead) | 3.8B |
| Variants | 1 |
| Runs with | transformers |
| Based on | Qwen/Qwen2.5-3B-Instruct |
| Released | 2026-03-02 |
| Popularity | 95k downloads / month |
| Likes | 2,972 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| LocateAnything-3B | 3.8B | BF16 | ~8.8 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys locateanything for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (locateanything below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"locateanything","messages":[{"role":"user","content":"Hello"}]}'
Details
Languages
Tags
Papers
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗