Qwen/Qwen3-Embedding-0.6B download history
Qwen/Qwen3-Embedding-0.6B is a 596M-parameter feature extraction model by Qwen. In the last 30 days it was downloaded 9,558,268 times (2,089,925 in the last 7 days), and 91,784,389 times in total.
It ranks #33 on the Hub by monthly downloads and #4 among feature extraction models.
It has 1,258 likes, 10 of them in the last week.
It is a fine-tune of Qwen/Qwen3-0.6B-Base.
578 models build on Qwen3-Embedding-0.6B: 310 quantized, 245 fine-tuned, 23 adapters and 0 merges. Together with the original they were downloaded 9,748,624 times in the last 30 days. See the Qwen3-Embedding-0.6B galaxy.
Most downloaded derivatives
- mhiveai/Qwen-Insure (finetune), 27.7K downloads in 30 days
- onnx-community/Qwen3-Embedding-0.6B-ONNX (quantized), 23.9K downloads in 30 days
- Octen/Octen-Embedding-0.6B (finetune), 23K downloads in 30 days
- mlx-community/Qwen3-Embedding-0.6B-4bit-DWQ (quantized), 22.2K downloads in 30 days
- pipizhao/SkillRouter-Embedding-0.6B (finetune), 17K downloads in 30 days
- mlx-community/Qwen3-Embedding-0.6B-8bit (finetune), 4.9K downloads in 30 days
- kwisschen/qwen3-embedding-0.6b-patent-oa-rejections (adapter), 4.3K downloads in 30 days
- furiosa-ai/Qwen3-Embedding-0.6B (finetune), 3.6K downloads in 30 days
- PeterAM4/Qwen3-Embedding-0.6B-GGUF (quantized), 2.7K downloads in 30 days
- OpenMed/OpenMed-PII-QwenMed-XLarge-600M-v1 (finetune), 2.3K downloads in 30 days
- futur/Qwen3-Embedding-0.6B-model2vec-onnx (quantized), 1.9K downloads in 30 days
- Hanno-Labs/dinghy-law-0.6b-v1 (finetune), 1.8K downloads in 30 days