Qwen/Qwen3-Embedding-8B download history

Qwen/Qwen3-Embedding-8B is a 7.6B-parameter feature extraction model by Qwen. In the last 30 days it was downloaded 2,136,953 times (395,283 in the last 7 days), and 27,927,754 times in total.

It ranks #186 on the Hub by monthly downloads and #12 among feature extraction models.

It has 861 likes, 5 of them in the last week.

It is a fine-tune of Qwen/Qwen3-8B-Base.

146 models build on Qwen3-Embedding-8B: 75 quantized, 51 fine-tuned, 20 adapters and 0 merges. Together with the original they were downloaded 2,351,526 times in the last 30 days. See the Qwen3-Embedding-8B 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 2026-11-182,136,953+2%
October 20262,097,943-18%
September 20262,554,391+5%
August 20262,439,989-29%
July 20263,429,609+46%
June 20262,341,584+47%
May 20261,590,392-18%
April 20261,945,391+18%
March 20261,651,905-12%
February 20261,871,984+7%
January 20261,745,069+80%
December 2025969,455+43%

Its busiest 30 days so far ended on 2026-07-30, with 3,433,656 downloads.

Open Qwen/Qwen3-Embedding-8B on Hugging Face

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