nvidia/LocateAnything-3B download history

nvidia/LocateAnything-3B is a 3.8B-parameter image text to text model by nvidia. In the last 30 days it was downloaded 32,250 times (9,241 in the last 7 days), and 2,611,044 times in total.

It ranks #4,784 on the Hub by monthly downloads and #632 among image text to text models.

It has 3,192 likes, 10 of them in the last week.

It is a fine-tune of Qwen/Qwen2.5-3B-Instruct.

44 models build on LocateAnything-3B: 28 quantized, 15 fine-tuned, 1 adapters and 0 merges. Together with the original they were downloaded 65,486 times in the last 30 days. See the LocateAnything-3B galaxy.

Most downloaded derivatives

Downloads by month

Downloads in the 30 days up to the end of each month, and the change from the month before.

MonthDownloadsChange
Up to 2026-11-1832,250-91%
October 2026377,461+846%
September 202639,906-58%
August 202694,216-88%
July 2026801,139+0%

Its busiest 30 days so far ended on 2026-07-18, with 1,734,269 downloads.

Open nvidia/LocateAnything-3B on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.