LocateAnything 3B is an open-source language model by nvidia. Features: 3b LLM, VRAM: 7.7GB, License: other, Instruction-Based, LLM Explorer Score: 0.49.
Arxiv:1405.0312 Arxiv:1908.03195 Arxiv:2109.10852 Arxiv:2303.05499 Arxiv:2504.07491 Arxiv:2504.07981 Arxiv:2510.12798 Arxiv:2605.27365 Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-3b-ins... Conversational Custom code Eagle En Feature-extraction Grounding Image-text-to-text Instruct Locateanything Nvidia Object-detection Region:us Safetensors Sharded Tensorflow Vision
Model Card on HF 🤗: https://huggingface.co/nvidia/LocateAnything-3B
LocateAnything 3B Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
LocateAnything 3B Parameters and Internals
| LLM Name | LocateAnything 3B |
| Repository 🤗 | https://huggingface.co/nvidia/LocateAnything-3B |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 7.7 GB |
| Updated | 2026-06-04 |
| Maintainer | nvidia |
| Model Type | locateanything |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | LocateAnythingForConditionalGeneration |
| License | other |
| Model Max Length | 16384 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Torch Data Type | bfloat16 |
| Errors | replace |
Rank the LocateAnything 3B Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 54290 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a