Qwen/Qwen3-Embedding-4B download history
Qwen/Qwen3-Embedding-4B is a 4.0B-parameter feature extraction model by Qwen. In the last 30 days it was downloaded 1,827,974 times (444,225 in the last 7 days), and 21,649,197 times in total.
It ranks #212 on the Hub by monthly downloads and #15 among feature extraction models.
It has 332 likes, 4 of them in the last week.
It is a fine-tune of Qwen/Qwen3-4B-Base.
147 models build on Qwen3-Embedding-4B: 65 quantized, 49 fine-tuned, 33 adapters and 0 merges. Together with the original they were downloaded 2,129,900 times in the last 30 days. See the Qwen3-Embedding-4B galaxy.
Most downloaded derivatives
- boboliu/Qwen3-Embedding-4B-W4A16-G128 (quantized), 262.6K downloads in 30 days
- Octen/Octen-Embedding-4B (finetune), 6.1K downloads in 30 days
- mlx-community/Qwen3-Embedding-4B-4bit-DWQ (quantized), 5.4K downloads in 30 days
- furiosa-ai/Qwen3-Embedding-4B (finetune), 4K downloads in 30 days
- Octen/Octen-Embedding-4B-INT8 (quantized), 1.7K downloads in 30 days
- drawais/Qwen3-Embedding-4B-AWQ-INT4 (quantized), 1.3K downloads in 30 days
- ufca-llms/jua-4B-mixed (finetune), 1.3K downloads in 30 days
- mradermacher/Qwen3-Embedding-4B-GGUF (quantized), 1.2K downloads in 30 days
- mradermacher/Qwen3-Embedding-4B-i1-GGUF (quantized), 1.2K downloads in 30 days
- Querit/Querit-4B (finetune), 1.1K downloads in 30 days
- QuaduxIT/Qwen3-Embedding-4B-W8A16 (quantized), 951 downloads in 30 days
- AQ-MedAI/Diver-Retriever-4B (finetune), 948 downloads in 30 days