Qwen/Qwen3-Embedding-8B download history
Qwen/Qwen3-Embedding-8B is a 7.6B-parameter feature extraction model by Qwen. In the last 30 days it was downloaded 2,587,093 times (444,616 in the last 7 days), and 24,602,357 times in total.
It ranks #152 on the Hub by monthly downloads and #9 among feature extraction models.
It has 819 likes, 8 of them in the last week.
It is a fine-tune of Qwen/Qwen3-8B-Base.
127 models build on Qwen3-Embedding-8B: 66 quantized, 45 fine-tuned, 16 adapters and 0 merges. Together with the original they were downloaded 3,703,237 times in the last 30 days. See the Qwen3-Embedding-8B galaxy.
Most downloaded derivatives
- Octen/Octen-Embedding-8B (finetune), 1M downloads in 30 days
- drawais/Qwen3-Embedding-8B-AWQ-INT4 (quantized), 20.2K downloads in 30 days
- alexliap/Qwen3-Embedding-8B-NVFP4 (quantized), 16K downloads in 30 days
- furiosa-ai/Qwen3-Embedding-8B (finetune), 4K downloads in 30 days
- alexliap/Qwen3-Embedding-8B-FP8-DYNAMIC (quantized), 3.4K downloads in 30 days
- mlx-community/Qwen3-Embedding-8B-4bit-DWQ (quantized), 2.3K downloads in 30 days
- Octen/Octen-Embedding-8B-INT8 (quantized), 1.7K downloads in 30 days
- mradermacher/Qwen3-Embedding-8B-i1-GGUF (quantized), 1.1K downloads in 30 days
- huynguyendbs/Qwen3-Embedding-8B-4bit-MLX (quantized), 689 downloads in 30 days
- mradermacher/Qwen3-Embedding-8B-GGUF (quantized), 643 downloads in 30 days
- LingoIITGN/qwen-indic-v1 (adapter), 518 downloads in 30 days
- Mira190/Euler-Legal-Embedding-V1 (finetune), 488 downloads in 30 days