Qwen/Qwen3-VL-Embedding-8B download history
Qwen/Qwen3-VL-Embedding-8B is an 8.1B-parameter sentence similarity model by Qwen. In the last 30 days it was downloaded 1,393,863 times (363,290 in the last 7 days), and 10,854,799 times in total.
It ranks #289 on the Hub by monthly downloads and #18 among sentence similarity models.
It has 486 likes, 3 of them in the last week.
It is a fine-tune of Qwen/Qwen3-VL-8B-Instruct.
26 models build on Qwen3-VL-Embedding-8B: 21 quantized, 5 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 1,630,205 times in the last 30 days. See the Qwen3-VL-Embedding-8B galaxy.
Most downloaded derivatives
- RamManavalan/Qwen3-VL-Embedding-8B-FP8 (quantized), 218K downloads in 30 days
- VesNFF/Qwen3-VL-Embedding-8B-GGUF (quantized), 8K downloads in 30 days
- mradermacher/Qwen3-VL-Embedding-8B-GGUF (quantized), 3.2K downloads in 30 days
- mradermacher/Qwen3-VL-Embedding-8B-i1-GGUF (quantized), 2K downloads in 30 days
- QuaduxIT/Qwen3-VL-Embedding-8B-W8A16 (quantized), 1.5K downloads in 30 days
- batiai/Qwen3-VL-Embedding-8B-GGUF (quantized), 737 downloads in 30 days
- dam2452/Qwen3-VL-Embedding-8B-GGUF (quantized), 544 downloads in 30 days
- gonuit/Qwen3-VL-Embedding-8B-AWQ-4bit (quantized), 521 downloads in 30 days
- collin-park/Qwen3-VL-Embedding-8B-W8A8 (quantized), 372 downloads in 30 days
- sywang/TPIPS-Embed-Qwen3VL-8B (finetune), 257 downloads in 30 days
- jedisct1/Qwen3-VL-Embedding-8B-mlx (quantized), 240 downloads in 30 days
- Zeknes/Qwen3-VL-Embedding-8B-MLX-4bit (quantized), 232 downloads in 30 days