Qwen/Qwen3-4B-Instruct-2507-FP8 download history

Qwen/Qwen3-4B-Instruct-2507-FP8 is a 4.4B-parameter text generation model by Qwen. In the last 30 days it was downloaded 1,610,219 times (432,386 in the last 7 days), and 10,505,133 times in total.

It ranks #251 on the Hub by monthly downloads and #39 among text generation models.

It has 92 likes, 1 of them in the last week.

It is a quantization of Qwen/Qwen3-4B-Instruct-2507.

8 models build on Qwen3-4B-Instruct-2507-FP8: 4 quantized, 1 fine-tuned, 0 adapters and 3 merges. Together with the original they were downloaded 1,613,834 times in the last 30 days. See the Qwen3-4B-Instruct-2507-FP8 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 2026-11-181,610,219+23%
October 20261,308,462+27%
September 20261,029,197-10%
August 20261,149,502+4%
July 20261,100,744+25%
June 2026877,575+1%
May 2026864,882+31%
April 2026661,621-7%
March 2026711,750+67%
February 2026427,314-24%
January 2026561,529+1059%
December 202548,466+26%

Its busiest 30 days so far ended on 2026-11-18, with 1,610,219 downloads.

Open Qwen/Qwen3-4B-Instruct-2507-FP8 on Hugging Face

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