mlx-community/Qwen2.5-0.5B-Instruct-4bit download history
mlx-community/Qwen2.5-0.5B-Instruct-4bit is a 494M-parameter text generation model by mlx-community. In the last 30 days it was downloaded 23,155 times (3,625 in the last 7 days), and 260,893 times in total.
It ranks #5,608 on the Hub by monthly downloads and #1,204 among text generation models.
It has 8 likes.
It is a fine-tune of Qwen/Qwen2.5-0.5B.
5 models build on Qwen2.5-0.5B-Instruct-4bit: 0 quantized, 2 fine-tuned, 3 adapters and 0 merges. Together with the original they were downloaded 23,184 times in the last 30 days. See the Qwen2.5-0.5B-Instruct-4bit galaxy.
Most downloaded derivatives
- YoozLabs/Yooz-Light-v2.1-Qwen2.5-0.5B (adapter), 12 downloads in 30 days
- jarkas/jilid_qwen2.5_0.5B_4bit (finetune), 9 downloads in 30 days
- YoozLabs/Yooz-Light-v2-Qwen2.5-0.5B-LoRA (adapter), 8 downloads in 30 days
- Lucas2021YT/Crystal-AI-0.5B (finetune), 0 downloads in 30 days
- victor/qwen2.5-0.5B-chess-lora (adapter), 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 | 23,155 | -48% |
| October 2026 | 44,625 | -10% |
| September 2026 | 49,638 | +125% |
| August 2026 | 22,097 | +39% |
| July 2026 | 15,898 | +6% |
| June 2026 | 14,991 | +4% |
| May 2026 | 14,383 | -1% |
| April 2026 | 14,527 | -7% |
| March 2026 | 15,554 | +149% |
| February 2026 | 6,250 | +56% |
| January 2026 | 4,015 | -27% |
| December 2025 | 5,483 | +24% |
Its busiest 30 days so far ended on 2026-10-14, with 73,873 downloads.
Open mlx-community/Qwen2.5-0.5B-Instruct-4bit on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.