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

Qwen/Qwen3-4B-Thinking-2507-FP8 is a 4.4B-parameter text generation model by Qwen. In the last 30 days it was downloaded 19,996 times (688 in the last 7 days), and 2,437,703 times in total.

It ranks #5,988 on the Hub by monthly downloads and #1,305 among text generation models.

It has 76 likes.

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

4 models build on Qwen3-4B-Thinking-2507-FP8: 2 quantized, 0 fine-tuned, 0 adapters and 2 merges. Together with the original they were downloaded 20,230 times in the last 30 days. See the Qwen3-4B-Thinking-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 2026-11-1819,996-34%
October 202630,341+261%
September 20268,398-90%
August 202680,329-61%
July 2026207,774+3%
June 2026201,114+11%
May 2026180,914-6%
April 2026193,051+2%
March 2026188,470+2%
February 2026184,603+18%
January 2026156,633-8%
December 2025170,718-8%

Its busiest 30 days so far ended on 2026-07-18, with 220,156 downloads.

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

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