DataLearner logoDataLearnerAI
Latest AI Insights
Model Evaluations
Model Directory
Model Comparison
Resource Center
Tool Directory

加载中...

DataLearner logoDataLearner AI

A knowledge platform focused on LLM benchmarking, datasets, and practical instruction with continuously updated capability maps.

产品

  • Leaderboards
  • 模型对比
  • Datasets

资源

  • Tutorials
  • Editorial
  • Tool directory

关于

  • 关于我们
  • 隐私政策
  • 数据收集方法
  • 联系我们

© 2026 DataLearner AI. DataLearner curates industry data and case studies so researchers, enterprises, and developers can rely on trustworthy intelligence.

隐私政策服务条款
Page navigation
目录
Model catalogQwen3-30B-A3B
QW

Qwen3-30B-A3B

Qwen3-30B-A3B

Release date: 2025-04-28更新于: 2025-07-30 11:29:301,852
Live demoGitHubHugging FaceCompare
Parameters
305.0亿
Context length
128K
Chinese support
Supported
Reasoning ability

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Qwen3-30B-A3B

Model basics

Reasoning traces
Supported
Context length
128K tokens
Max output length
16384 tokens
Model type
推理大模型
Release date
2025-04-28
Model file size
61.09 GB
MoE architecture
Yes
Total params / Active params
305.0B / 33B
Knowledge cutoff
No data
Inference modes
常规模式（Non-Thinking Mode）思考模式（Thinking Mode）
Qwen3-30B-A3B

Open source & experience

Code license
Apache 2.0
Weights license
Apache 2.0- 免费商用授权
GitHub repo
https://github.com/QwenLM/Qwen3
Hugging Face
https://huggingface.co/Qwen/Qwen3-30B-A3B
Live demo
No live demo
Qwen3-30B-A3B

Official resources

Paper
Qwen3: Think Deeper, Act Faster
DataLearnerAI blog
重磅！阿里开源第三代千问大模型：Qwen3系列，最小仅6亿参数规模，最大2350亿参数规模大模型！
Qwen3-30B-A3B

API details

API speed
4/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard pricingStandard
ModalityInputOutput
Text$0.2$0.8
Qwen3-30B-A3B

Benchmark Results

综合评估

3 evaluations
Benchmark / mode
Score
Rank/total
MMLU ProNormal
69.10
78 / 112
LiveBenchNormal
57.80
49 / 52
GPQA DiamondNormal
54.80
122 / 153

编程与软件工程

1 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBenchNormal
29
101 / 103

数学推理

1 evaluations
Benchmark / mode
Score
Rank/total
AIME2025Normal
21.60
103 / 105

写作和创作

1 evaluations
Benchmark / mode
Score
Rank/total
Creative WritingNormal
68.10
21 / 22
查看评测深度分析与其他模型对比
Qwen3-30B-A3B

Publisher

阿里巴巴
阿里巴巴
View publisher details
Qwen3-30B-A3B

Model Overview

Qwen3-30B-A3B是阿里开源的第三代千问大模型中的MoE架构版本的模型，参数300亿，每次推理激活其中的30亿参数。


2025年7月29日，阿里发布了这个模型的更新版本，仅支持非推理模式的Qwen3-30B-A3B-Instruct-2507，但是各方面能力提升明显。

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送

DataLearner 官方微信二维码