mlx-community/Qwen3-1.7B-4bit download history
mlx-community/Qwen3-1.7B-4bit is a 1.7B-parameter text generation model by mlx-community. In the last 30 days it was downloaded 15,061 times (3,962 in the last 7 days), and 325,862 times in total.
It ranks #6,660 on the Hub by monthly downloads and #1,511 among text generation models.
It has 7 likes.
It is a quantization of Qwen/Qwen3-1.7B.
13 models build on Qwen3-1.7B-4bit: 7 quantized, 1 fine-tuned, 5 adapters and 0 merges. Together with the original they were downloaded 15,373 times in the last 30 days. See the Qwen3-1.7B-4bit galaxy.
Most downloaded derivatives
- guiltylemon/gno-expansion-slim-retrieval-v1 (quantized), 92 downloads in 30 days
- everscending/qwen3-1.7b-article-usage-micro-coach (finetune), 61 downloads in 30 days
- imYChaudhary22/zen-polish-v2-1.7b-4bit (quantized), 49 downloads in 30 days
- imYChaudhary22/zen-polish-v22-4bit (adapter), 23 downloads in 30 days
- alan13367/iMLX-Qwen3-1.7B-Current-Tools-8bit (quantized), 22 downloads in 30 days
- Nerdstorm/Qwen3-1.7B-MLX-4bit-OpenVINO (adapter), 14 downloads in 30 days
- atakle/socratic-tutor-judge-v9-1.7b (quantized), 14 downloads in 30 days
- atakle/socratic-tutor-rewriter-v4-1.7b (quantized), 12 downloads in 30 days
- cagataydev/doer (adapter), 11 downloads in 30 days
- ilanuzan/steve-qwen3-1.7b-fused (quantized), 7 downloads in 30 days
- Juhuu/slowestlooser-v5-4bit (adapter), 5 downloads in 30 days
- alan13367/iMLX-Qwen3-1.7B-4bit (quantized), 2 downloads in 30 days