mlx-community/Qwen3-8B-4bit download history
mlx-community/Qwen3-8B-4bit is an 8.2B-parameter text generation model by mlx-community. In the last 30 days it was downloaded 35,302 times (9,424 in the last 7 days), and 437,494 times in total.
It ranks #4,575 on the Hub by monthly downloads and #976 among text generation models.
It has 20 likes.
It is a quantization of Qwen/Qwen3-8B.
6 models build on Qwen3-8B-4bit: 1 quantized, 0 fine-tuned, 5 adapters and 0 merges. Together with the original they were downloaded 39,784 times in the last 30 days. See the Qwen3-8B-4bit galaxy.
Most downloaded derivatives
- VertexAGI/prism-roleplay-1.5-small (adapter), 1.9K downloads in 30 days
- VertexAGI/prism-roleplay-1-small (adapter), 1.2K downloads in 30 days
- VertexAGI/codeinswift-1-small (adapter), 659 downloads in 30 days
- VertexAGI/codeinluau-1-small (adapter), 651 downloads in 30 days
- spanthee/qwen3-macos-clawdia-toolcalling-mlx-4bit (quantized), 50 downloads in 30 days
- Fenomen-Alex/ukrainian-municipal-accountability-qwen3-8b (adapter), 41 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 | 35,302 | +5% |
| October 2026 | 33,584 | -79% |
| September 2026 | 161,741 | +313% |
| August 2026 | 39,127 | +12% |
| July 2026 | 34,856 | +40% |
| June 2026 | 24,981 | +18% |
| May 2026 | 21,152 | +50% |
| April 2026 | 14,121 | -35% |
| March 2026 | 21,836 | -13% |
| February 2026 | 25,145 | +493% |
| January 2026 | 4,238 | +56% |
| December 2025 | 2,714 | +53% |
Its busiest 30 days so far ended on 2026-10-08, with 167,035 downloads.
Open mlx-community/Qwen3-8B-4bit on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.