Latest AI Insights

Model Evaluations

Model Directory

Model Comparison

Resource Center

Search blog

加载中...

DataLearner 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

Qwen2-72B - AI Model Details and Benchmarks | DataLearnerAI

Page navigation

目录

Model catalogQwen2-72B

QW

Qwen2-72B

Qwen2-72B

Release date: 2024-06-07更新于: 2024-06-09 21:25:31487

Live demo GitHub Hugging Face Compare

Parameters

727.0亿

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

Qwen2-72B

Model basics

Reasoning traces

Not supported

Context length

128K tokens

Max output length

No data

Model type

基础大模型

Release date

2024-06-07

Model file size

Qwen2-72B

Open source & experience

Code license

Tongyi Qianwen LICENSE AGREEMENT

Weights license

Tongyi Qianwen LICENSE AGREEMENT- 免费商用授权

GitHub repo

https://github.com/QwenLM/Qwen2

Hugging Face

https://huggingface.co/Qwen/Qwen2-72B

Qwen2-72B

Official resources

Paper

DataLearnerAI blog

阿里巴巴开源第二代大语言模型Qwen2系列，最高参数规模700亿，评测结果位列开源模型第一，超过了Meta开源的Llama3-70B！

Qwen2-72B

API details

API speed

No data

No public API pricing yet.

Qwen2-72B

Benchmark Results

No benchmark data to show.

Qwen2-72B

Publisher

阿里巴巴

View publisher details

Qwen2-72B

Model Overview

阿里巴巴开源的第二代大语言模型，Qwen2系列中720亿参数规模版本的大模型。在多项评测任务中都超过了同等级别的开源模型，如Llama3-70B、Mixtral-8×22B、Qwen1.5-110B等。

阿里也同时开源了基于Qwen2-72B进行对话微调的版本，即Qwen2-72B-Instruct，该版本可以直接用来对话，其MT-Bench得分9.12分，仅次于GPT-4-0613，超过了GPT-4-0314版本！

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

145GB

MoE architecture

No

Total params / Active params

727.0B / N/A

Knowledge cutoff

No data

Inference modes

No mode data

Live demo

https://huggingface.co/spaces/Qwen/Qwen2-72B-Instruct