mlx-community/Qwen2.5-7B-Instruct-4bit download history
mlx-community/Qwen2.5-7B-Instruct-4bit is a 7.6B-parameter text generation model by mlx-community. In the last 30 days it was downloaded 12,587 times (2,992 in the last 7 days), and 557,745 times in total.
It ranks #7,508 on the Hub by monthly downloads and #1,676 among text generation models.
It has 18 likes, 1 of them in the last week.
It is a fine-tune of Qwen/Qwen2.5-7B.
6 models build on Qwen2.5-7B-Instruct-4bit: 4 quantized, 0 fine-tuned, 2 adapters and 0 merges. Together with the original they were downloaded 12,653 times in the last 30 days. See the Qwen2.5-7B-Instruct-4bit galaxy.
Most downloaded derivatives
- RaghaMounam/Qwen2.5-Email-Order-details-Extractor-v1 (quantized), 23 downloads in 30 days
- nnnnnzo/titan-titanic-oracle (adapter), 19 downloads in 30 days
- Dellboy/chem_sage_7b_v1 (quantized), 16 downloads in 30 days
- LeThuong2209/logicmodel (quantized), 8 downloads in 30 days
- Filipelac/nexoverdict-adapters (adapter), 0 downloads in 30 days
- pphothidaen/qwen2.5-7b-bazi-instruct-4bit (quantized), 0 downloads in 30 days
Downloads by month
Downloads in the 30 days up to the end of each month, and the change from the month before.
| Month | Downloads | Change |
|---|---|---|
| Up to 2026-11-18 | 12,587 | -12% |
| October 2026 | 14,231 | -21% |
| September 2026 | 17,906 | +4% |
| August 2026 | 17,182 | -9% |
| July 2026 | 18,816 | +12% |
| June 2026 | 16,836 | +23% |
| May 2026 | 13,675 | -4% |
| April 2026 | 14,239 | +24% |
| March 2026 | 11,510 | -9% |
| February 2026 | 12,624 | +194% |
| January 2026 | 4,289 | -41% |
| December 2025 | 7,316 | +649% |
Its busiest 30 days so far ended on 2025-01-29, with 280,497 downloads.
Open mlx-community/Qwen2.5-7B-Instruct-4bit on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.