ByteDance/Sa2VA-Qwen3-VL-4B download history

ByteDance/Sa2VA-Qwen3-VL-4B is a 5.1B-parameter image text to text model by ByteDance. In the last 30 days it was downloaded 962 times (273 in the last 7 days), and 21,924 times in total.

It ranks #40,317 on the Hub by monthly downloads and #3,039 among image text to text models.

It has 20 likes.

It is a merge of OpenGVLab/InternVL3-8B.

2 models build on Sa2VA-Qwen3-VL-4B: 0 quantized, 2 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 973 times in the last 30 days. See the Sa2VA-Qwen3-VL-4B galaxy.

Most downloaded derivatives

Open ByteDance/Sa2VA-Qwen3-VL-4B on Hugging Face