← 模型广场

Qwen: Qwen3 VL 30B A3B Instruct

qwen/qwen3-vl-30b-a3b-instruct

图像理解工具调用JSON流式

Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...

价格

输入

$0.13 / 1M

输出

$0.52 / 1M

参数

上下文

262,144 tokens

输入模态

text, image

输出模态

text

知识截止:2025-03-31

发布:2025-10

支持参数

frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

开放权重 · HuggingFace

1,147,218 月下载
574 收藏
apache-2.0 image-text-to-text
在 HuggingFace 查看 →