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

Qwen/Qwen2.5-72B-Instruct is a 72.7B-parameter text generation model by Qwen. In the last 30 days it was downloaded 157,310 times (44,558 in the last 7 days), and 9,201,538 times in total.

It ranks #1,756 on the Hub by monthly downloads and #352 among text generation models.

It has 1,047 likes, 3 of them in the last week.

It is a fine-tune of Qwen/Qwen2.5-72B.

695 models build on Qwen2.5-72B-Instruct: 353 quantized, 68 fine-tuned, 224 adapters and 50 merges. Together with the original they were downloaded 521,239 times in the last 30 days. See the Qwen2.5-72B-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 2026-11-18157,310-19%
October 2026194,213-35%
September 2026297,949-27%
August 2026406,675-19%
July 2026500,541-22%
June 2026637,646-29%
May 2026899,842+97%
April 2026456,124-34%
March 2026691,096+32%
February 2026524,389+94%
January 2026270,182-43%
December 2025477,329-11%

Its busiest 30 days so far ended on 2026-05-23, with 899,842 downloads.

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

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