← 模型广场

Qwen: Qwen3 Coder 30B A3B Instruct

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

工具调用JSON流式

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...

价格

输入

$0.07 / 1M

输出

$0.27 / 1M

参数

上下文

160,000 tokens

输入模态

text

输出模态

text

知识截止:2025-06-30

发布:2025-07

支持参数

frequency_penaltymax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

开放权重 · HuggingFace

1,962,787 月下载
1,085 收藏
apache-2.0 text-generation
在 HuggingFace 查看 →