AImodelsComparison.com 1,011 models
Menu
Models Best of Trending Can I run it? Methodology About
nvidia / image-text-to-text updated 1 month ago

LocateAnything-3B

🚀 Online Demo: LocateAnything (Hugging Face Spaces) 💻 GitHub Code: NVlabs/Eagle/Embodied 📄 Paper: arXiv:2605.27365

Params
3.8 B
Context
—
Downloads 30d
923 K
Likes
2,814
Licence: other Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days
1.1 M923 K
Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors bf16 7.7 GB 9.5 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture
LocateAnythingForConditionalGeneration
Parameters
3.8 B
Tensor type
BF16
Licence
other
First seen on the Hub
2026-03-02
Base model
Qwen2.5-3B-Instruct
Training datasets
undisclosed
Added to our catalog
2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Base Qwen2.5-3B-Instruct Qwen 6.0 M
Compare with
gemma-4-31B-it 11.9 M Qwen3.6-35B-A3B-FP8 8.9 M Qwen2.5-VL-3B-Instruct 8.2 M Qwen3.6-27B-FP8 7.8 M Qwen3.6-27B 7.0 M Qwen3.6-35B-A3B 5.9 M
Appears in
Best open coding models Commercial-use text models Models that fit in 12 GB
Sponsored · GPU cloud
Not enough VRAM?
Spin up a 24 GB L4 instance in 40 seconds. $0.44/hr.