mlx-community/Qwen2.5-Coder-7B-Instruct-4bit download history

mlx-community/Qwen2.5-Coder-7B-Instruct-4bit is a 7.6B-parameter text generation model by mlx-community. In the last 30 days it was downloaded 262,556 times (61,812 in the last 7 days), and 1,254,802 times in total.

It ranks #1,242 on the Hub by monthly downloads and #256 among text generation models.

It has 34 likes, 2 of them in the last week.

It is a fine-tune of Qwen/Qwen2.5-Coder-7B.

13 models build on Qwen2.5-Coder-7B-Instruct-4bit: 9 quantized, 2 fine-tuned, 2 adapters and 0 merges. Together with the original they were downloaded 263,839 times in the last 30 days. See the Qwen2.5-Coder-7B-Instruct-4bit 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 2026-11-18262,556+2%
October 2026258,675+1%
September 2026257,302+44%
August 2026178,508+456%
July 202632,094+147%
June 202612,983+67%
May 20267,775+41%
April 20265,514+36%
March 20264,047+46%
February 20262,777+235%
January 2026829+80%
December 2025460+42%

Its busiest 30 days so far ended on 2026-11-08, with 264,233 downloads.

Open mlx-community/Qwen2.5-Coder-7B-Instruct-4bit on Hugging Face

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