Qwen/Qwen2-VL-2B-Instruct download history

Qwen/Qwen2-VL-2B-Instruct is a 2.2B-parameter image text to text model by Qwen. In the last 30 days it was downloaded 981,215 times (211,696 in the last 7 days), and 51,170,650 times in total.

It ranks #413 on the Hub by monthly downloads and #72 among image text to text models.

It has 529 likes.

It is a fine-tune of Qwen/Qwen2-VL-2B.

683 models build on Qwen2-VL-2B-Instruct: 180 quantized, 263 fine-tuned, 239 adapters and 1 merges. Together with the original they were downloaded 1,401,948 times in the last 30 days. See the Qwen2-VL-2B-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 2026-11-18981,215-6%
October 20261,047,786-39%
September 20261,726,736-3%
August 20261,781,978-41%
July 20263,009,714-18%
June 20263,675,633+5%
May 20263,515,078-12%
April 20263,987,867+71%
March 20262,328,885-28%
February 20263,215,946+96%
January 20261,639,411-0%
December 20251,642,868-21%

Its busiest 30 days so far ended on 2025-09-20, with 4,601,823 downloads.

Open Qwen/Qwen2-VL-2B-Instruct on Hugging Face

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