LocateAnything-3B

s-a-i/LocateAnything-3B

Image Text to Text3.8B parameterstransformersLicense: otherGated

Tracked by OpenModelStats since September 11, 2026View on Hugging Face ↗

Downloads 30D: 0
Total downloads: 0
Gained 7D: 0
Gained 30D: —
Likes: 0; +0 in 7D
Rank · tracked models: —; –this week
Parameters: 3.8B
Last source update: Aug 30, 2026

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-09-11. Charts appear as daily observations accumulate.

Overview

LocateAnything-3B is a image text to text model published by s-a-i. OpenModelStats has tracked the model since Sep 11, 2026, most recently observing it Aug 31, 2026.

Published: Aug 29, 2026
Last updated: Aug 30, 2026
Library: transformers
License: other
Task: Image Text to Text
Parameters: 3,830,665,968
Spaces: —
Derivative models: —
Velocity 7D/day: 0

transformerssafetensorslocateanythingfeature-extractionnvidiaeaglevisionobject-detectiongroundingarxiv:2605.27365image-text-to-textconversational

Publisher

s-a-iView publisher statistics →

Derived from Qwen/Qwen2.5-3B-Instruct (reported by the source; parent not yet tracked).

Similar models

Models similar to LocateAnything-3B
Model	Task	DL 30D	Likes	Params
LocateAnything-3Bnvidia	Image Text to Text	272.3K	3,109	3.8B
TinyLLaVA-Qwen2.5-3B-SigLIPZhang199	Image Text to Text	1,292	0	3.8B
Qwen2.5-VL-3B-Instruct-unsloth-bnb-4bitunsloth	Image Text to Text	5,551	16	3.8B
Qwen3.8-27B-MLX-3bit-CLIP-DWQAtomicChat	Image Text to Text	0	0	3.8B
Ristretto-3BLiAutoAD	Image Text to Text	3,055	10	3.8B
Super-Slop-Machina-RP-XXL-Small-3B-2608Indexnusrefather	Image Text to Text	620	3	3.8B