Qwen/Qwen2.5-VL-72B-Instruct download history

Qwen/Qwen2.5-VL-72B-Instruct is a 73.4B-parameter image text to text model by Qwen. In the last 30 days it was downloaded 65,744 times (9,425 in the last 7 days), and 7,733,790 times in total.

It ranks #3,258 on the Hub by monthly downloads and #416 among image text to text models.

It has 668 likes, 1 of them in the last week.

90 models build on Qwen2.5-VL-72B-Instruct: 54 quantized, 22 fine-tuned, 14 adapters and 0 merges. Together with the original they were downloaded 122,861 times in the last 30 days. See the Qwen2.5-VL-72B-Instruct 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 2026-11-1865,744-34%
October 2026100,030+33%
September 202675,382-68%
August 2026236,513-60%
July 2026588,049+38%
June 2026427,364+67%
May 2026255,502+134%
April 2026109,159+1%
March 2026107,734-67%
February 2026328,282+163%
January 2026124,713+76%
December 202570,774-70%

Its busiest 30 days so far ended on 2025-08-25, with 909,746 downloads.

Open Qwen/Qwen2.5-VL-72B-Instruct on Hugging Face

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