仅4B！阿里千问最强视觉模型新开源，网友：我的16GB Mac有救了

智东西10-15

作者 | 李水青编辑 | 心缘智东西10月15日报道，今日，阿里通义千问团队推出其最强视觉语言模型系列Qwen3-VL的4B与8B版本，两个尺寸均提供Instruct与Thinking版本，在几十项权威基准测评中超越Gemini 2.5 Flash Lite、GPT-5 Nano等同级别顶尖模型。阿里千问团队公告截图（图源：X平台）这两个新版本模型实现了以下关键目标:1、资源门槛更低：尺寸缩减显著...

网页链接

免责声明：本文观点仅代表作者个人观点，不构成本平台的投资建议，本平台不对文章信息准确性、完整性和及时性做出任何保证，亦不对因使用或信赖文章信息引发的任何损失承担责任。

精彩评论

我们需要你的真知灼见来填补这片空白

发表看法

{"i18n":{"language":"zh_CN"},"isChannel":false,"data":{"share":"https://www.laohu8.com/m/news/2575272484?lang=zh_CN&edition=full","thumbnail":"","is_english":false,"pubTime":"2025-10-15 12:48","share_image_url":"https://static.laohu8.com/e9f99090a1c2ed51c021029395664489","id":"2575272484","market":"hk","top_or_hot":-1,"title":"仅4B！阿里千问最强视觉模型新开源，网友：我的16GB Mac有救了","media":"智东西","content":"<div>\n<p>作者 | 李水青编辑 | 心缘智东西10月15日报道，今日，阿里通义千问团队推出其最强视觉语言模型系列Qwen3-VL的4B与8B版本，两个尺寸均提供Instruct与Thinking版本，在几十项权威基准测评中超越Gemini 2.5 Flash Lite、GPT-5 Nano等同级别顶尖模型。阿里千问团队公告截图（图源：X平台）这两个新版本模型实现了以下关键目标:1、资源门槛更低：尺寸缩减显著...</p>\n\n<a href=\"https://tech.ifeng.com/c/8nTFRU7dZXB\">网页链接</a>\n\n</div>\n","source":"fenghuang_stock","html":"<!DOCTYPE html>\n<html>\n<head>\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n<meta name=\"viewport\" content=\"width=device-width,initial-scale=1.0,minimum-scale=1.0,maximum-scale=1.0,user-scalable=no\"/>\n<meta name=\"format-detection\" content=\"telephone=no,email=no,address=no\" />\n<title>仅4B！阿里千问最强视觉模型新开源，网友：我的16GB Mac有救了</title>\n<style type=\"text/css\">\na,abbr,acronym,address,applet,article,aside,audio,b,big,blockquote,body,canvas,caption,center,cite,code,dd,del,details,dfn,div,dl,dt,\nem,embed,fieldset,figcaption,figure,footer,form,h1,h2,h3,h4,h5,h6,header,hgroup,html,i,iframe,img,ins,kbd,label,legend,li,mark,menu,nav,\nobject,ol,output,p,pre,q,ruby,s,samp,section,small,span,strike,strong,sub,summary,sup,table,tbody,td,tfoot,th,thead,time,tr,tt,u,ul,var,video{ font:inherit;margin:0;padding:0;vertical-align:baseline;border:0 }\nbody{ font-size:16px; line-height:1.5; color:#999; background:transparent; }\n.wrapper{ overflow:hidden;word-break:break-all;padding:10px; }\nh1,h2{ font-weight:normal; line-height:1.35; margin-bottom:.6em; }\nh3,h4,h5,h6{ line-height:1.35; margin-bottom:1em; }\nh1{ font-size:24px; }\nh2{ font-size:20px; }\nh3{ font-size:18px; }\nh4{ font-size:16px; }\nh5{ font-size:14px; }\nh6{ font-size:12px; }\np,ul,ol,blockquote,dl,table{ margin:1.2em 0; }\nul,ol{ margin-left:2em; }\nul{ list-style:disc; }\nol{ list-style:decimal; }\nli,li p{ margin:10px 0;}\nimg{ max-width:100%;display:block;margin:0 auto 1em; }\nblockquote{ color:#B5B2B1; border-left:3px solid #aaa; padding:1em; }\nstrong,b{font-weight:bold;}\nem,i{font-style:italic;}\ntable{ width:100%;border-collapse:collapse;border-spacing:1px;margin:1em 0;font-size:.9em; }\nth,td{ padding:5px;text-align:left;border:1px solid #aaa; }\nth{ font-weight:bold;background:#5d5d5d; }\n.symbol-link{font-weight:bold;}\n/* header{ border-bottom:1px solid #494756; } */\n.title{ margin:0 0 8px;line-height:1.3;color:#ddd; }\n.meta {color:#5e5c6d;font-size:13px;margin:0 0 .5em; }\na{text-decoration:none; color:#2a4b87;}\n.meta .head { display: inline-block; overflow: hidden}\n.head .h-thumb { width: 30px; height: 30px; margin: 0; padding: 0; border-radius: 50%; float: left;}\n.head .h-content { margin: 0; padding: 0 0 0 9px; float: left;}\n.head .h-name {font-size: 13px; color: #eee; margin: 0;}\n.head .h-time {font-size: 11px; color: #7E829C; margin: 0;line-height: 11px;}\n.small {font-size: 12.5px; display: inline-block; transform: scale(0.9); -webkit-transform: scale(0.9); transform-origin: left; -webkit-transform-origin: left;}\n.smaller {font-size: 12.5px; display: inline-block; transform: scale(0.8); -webkit-transform: scale(0.8); transform-origin: left; -webkit-transform-origin: left;}\n.bt-text {font-size: 12px;margin: 1.5em 0 0 0}\n.bt-text p {margin: 0}\n</style>\n</head>\n<body>\n<div class=\"wrapper\">\n<header>\n<h2 class=\"title\">\n仅4B！阿里千问最强视觉模型新开源，网友：我的16GB Mac有救了\n</h2>\n\n<h4 class=\"meta\">\n\n\n2025-10-15 12:48 北京时间&nbsp;&nbsp;&nbsp;<a href=https://tech.ifeng.com/c/8nTFRU7dZXB><strong>智东西</strong></a>\n\n\n</h4>\n\n</header>\n<article>\n<div>\n<p>作者 | 李水青编辑 | 心缘智东西10月15日报道，今日，阿里通义千问团队推出其最强视觉语言模型系列Qwen3-VL的4B与8B版本，两个尺寸均提供Instruct与Thinking版本，在几十项权威基准测评中超越Gemini 2.5 Flash Lite、GPT-5 Nano等同级别顶尖模型。阿里千问团队公告截图（图源：X平台）这两个新版本模型实现了以下关键目标:1、资源门槛更低：尺寸缩减显著...</p>\n\n<a href=\"https://tech.ifeng.com/c/8nTFRU7dZXB\">网页链接</a>\n\n</div>\n\n\n</article>\n</div>\n</body>\n</html>\n","isBrief":false,"type":0,"news_type":1,"symbol":"BK4565","symbol_name":"NFT概念","start_time":0,"source_url":"https://tech.ifeng.com/c/8nTFRU7dZXB","article_id":"2575272484","we_media_id":null,"thumbnails":[],"rights":null,"url":"https://stock-news.laohu8.com/highlight/detail?id=2575272484","pubTimestamp":1760503689,"columns":[],"sourceInfo":{"source_id":"fenghuang_stock","name":"凤凰网"},"weMediaInfo":null,"summary":"作者 | 李水青编辑 | 心缘智东西10月15日报道，今日，阿里通义千问团队推出其最强视觉语言模型系列Qwen3-VL的4B与8B版本，两个尺寸均提供Instruct与Thinking版本，在几十项权威基准测评中超越Gemini 2.5 Flash Lite、GPT-5 Nano等同级别顶尖模型。不少人对此表示一直在等这个，有人称：“终于，我在16GB的Mac上可以用了。”外网用户对新版本Qwen3-VL的评论自9月24日阿里开源Qwen3-VL系列以来，作为Qwen系列中最强的视觉语言模型，该模型在全球AI开源社区中快速收获认可。","collect":0,"end_time":0,"defaultTopTitle":"ifeng.com","property":[],"viewcount":null,"language":"zh","relate_stocks":{"300109":"新开源","BK4565":"NFT概念","LU0545039389.USD":"BGF GLOBAL EQUITY INCOME \"A2\" ACC","LU1769817096.USD":"UBS (LUX) EQUITY SICAV - GLOBAL EMERG MARKETS OPPO \"P\" (USD) INC","LU0106959298.USD":"UBS (LUX) EQUITY FUND - EMERGING MARKETS SUSTAINABLE LEADERS (USD) \"P\" (USD) ACC","BK4607":"DeepSeek概念股","BABA":"阿里巴巴","LU1282648689.USD":"ALLIANZ TOTAL RETURN ASIAN EQUITY \"AMG\" (USD) INC","LU0348816934.USD":"ALLIANZ TOTAL RETURN ASIAN EQUITY \"AT\" (USD)","LU1769817179.HKD":"UBS (LUX) EQUITY SICAV - GLOBAL EMERG MARKETS OPPO \"P\" (HKD) INC","LU1267930227.SGD":"TEMPLETON GLOBAL BALANCED \"AS\" (SGD) ACC A","BK4220":"综合零售","LU1242518857.USD":"FULLERTON LUX FUNDS - ASIA ABSOLUTE ALPHA \"I\" (USD) ACC","LU1046422090.SGD":"Fidelity Pacific A-SGD","LU0651947912.USD":"BGF EMERGING MARKETS EQUITY INCOME \"A5G\" (USD) INC","LU0128525689.USD":"TEMPLETON GLOBAL BALANCED \"A\"(USD) ACC","BK4531":"中概回港概念","BK4526":"热门中概股","LU0067412154.USD":"UBS (LUX) EQUITY FUND -  CHINA OPPORTUNITY \"P\" (USD) ACC","BK4585":"ETF&股票定投概念","LU0501845795.SGD":"瑞银大中华区股票基金P Acc SGD","LU0052756011.USD":"TEMPLETON GLOBAL BALANCED \"A\" (USD) INC","LU1051769294.HKD":"BGF EMERGING MARKETS EQUITY INCOME \"A6\"(HKDHDG) INC","BK4503":"景林资产持仓","LU0651946864.USD":"贝莱德新兴市场股票收益A2","LU1152091754.HKD":"UBS (LUX) EQUITY FUND - CHINA OPPORTUNITY (USD) \"PM\" (HKD) INC","LU2226246903.HKD":"ALLIANZ TOTAL RETURN ASIAN EQUITY \"AT4\" (HKD) ACC","LU1048588211.SGD":"Blackrock Asian Dragon A2 SGD-H","BK4575":"芯片概念","LU1880383366.USD":"东方汇理中国股票基金 A2 (C)","BK4558":"双十一","BK4587":"ChatGPT概念","BK4502":"阿里概念","LU1051768304.USD":"贝莱德新兴市场股票收益A6","LU0979878070.USD":"FULLERTON LUX FUNDS - ASIA ABSOLUTE ALPHA \"A\" (USD) ACC","LU0072462343.USD":"贝莱德亚洲巨龙基金","LU1823568750.SGD":"Fidelity Global Technology A-ACC SGD","LU0738911758.USD":"Blackrock Global Equity Income A6 USD","09988":"阿里巴巴-W","BK0046":"生物疫苗","BK0229":"化学制品","LU1515016050.SGD":"Blackrock Emerging Markets Equity Income A6 SGD-H","LU1003077747.HKD":"BGF GLOBAL EQUITY INCOME \"A6\" (HKDHDG) INC","LU0880133367.SGD":"UBS (LUX) EQUITY FUND CHINA OPPORTUNITY USD \"P\" (SGD) ACC","LU0553294199.USD":"BGF GLOBAL EQUITY INCOME \"A5G\" (USD) INC","BK4614":"Manus概念股","LU1105468828.SGD":"Allianz Total Return Asian Equity AM DIS H2-SGD","BK4548":"巴美列捷福持仓","LU1235294995.USD":"FIDELITY GLOBAL TECHNOLOGY \"A\" (USDHDG) ACC"},"translate_title":"4B only! Alibaba Qianwen's strongest visual model is newly open source, netizen: My 16GB Mac is saved","themeId":null,"isJumpTheme":false,"ttsUrl":null,"symbols_score_info":{"300109":1.5,"BABA":1.5,"ALBmain":0.6,"09988":0.6},"content_text":"作者 | 李水青编辑 | 心缘智东西10月15日报道，今日，阿里通义千问团队推出其最强视觉语言模型系列Qwen3-VL的4B与8B版本，两个尺寸均提供Instruct与Thinking版本，在几十项权威基准测评中超越Gemini 2.5 Flash Lite、GPT-5 Nano等同级别顶尖模型。阿里千问团队公告截图（图源：X平台）这两个新版本模型实现了以下关键目标:1、资源门槛更低：尺寸缩减显著降低VRAM的占用。现在，开发者可以在更广泛的硬件设备上部署和运行模型。2、核心能力不减配：在缩减尺寸的同时，其完整保留了Qwen3-VL的全部核心功能。3、基准性能优秀：在STEM、VQA、OCR、视频理解及Agent任务等多个权威基准上，其表现不仅超越了Gemini 2.5 Flash Lite和GPT-5 Nano，在许多场景下甚至能与阿里半年前的旗舰模型Qwen2.5-VL-72B相媲美。如下图所示，在多模态性能方面，Qwen3-VL-8B Instruct在MIABench、OCRBench、SUNRGBD、ERQA、VideoMMMU、ScreenSpot等30项权威基准测评中取得SOTA（行业最佳）成绩，超越了Gemini 2.5 Flash Lite、GPT-5 Nano以及Qwen2.5-VL-72B等顶尖模型。Qwen3-VL-8B Instruct与Qwen3-VL-4B Instruct基准测评情况（图源：Qwen）Qwen3-VL-4B Instruct也展现出优秀的多模态性能，以更少的参数量，在STEM、VQA、OCR、视频理解及Agent任务等测评中，能与Gemini 2.5 Flash Lite、GPT-5 Nano对打。在纯文本表现上，如下图所示，Qwen3-VL-8B Instruct和Qwen3-VL-4B Instruct也相比Qwen3-4B Instruct-2507和Qwen3-8B Non-Thinking有整体提高。Qwen3-VL-8B Instruct与Qwen3-VL-4B Instruct基准测评情况（图源：Qwen）在多模态性能方面，Qwen3-VL-8B Thinking取得了MathVision、MMStar、HallusionBench、MM-MT-Bench、CountBench等23项权威基准测评的SOTA，超越Gemini 2.5 Flash Lite、GPT-5 Nano高版本以及其他同等级顶尖开源模型。Qwen3-VL-4B Thinking同样表现出“以小敌大”的成绩。Qwen3-VL-8B Thinking与Qwen3-VL-4B Thinking基准测评情况（图源：Qwen）在纯文本表现上，Qwen3-VL-8B Thinking和Qwen3-VL-4B Thinking相比于Qwen3-4BThinking-2507和Qwen3-8B Thinking有整体提高。Qwen3-VL-8B Thinking与Qwen3-VL-4B Thinking基准测评情况（图源：Qwen）该模型一经发布，就在外网引起了不少开发者关注。不少人对此表示一直在等这个，有人称：“终于，我在16GB的Mac上可以用了。”也有不少人开始催更Qwen3-Max及其他更多版本模型了。外网用户对新版本Qwen3-VL的评论（图源：X平台）自9月24日阿里开源Qwen3-VL系列以来，作为Qwen系列中最强的视觉语言模型，该模型在全球AI开源社区中快速收获认可。（《阿里又一大模型开源，手机电脑样样玩的溜，多项测试秒GPT-5》）在9月底的Chatbot Arena子榜单Vision Arena中，Qwen3-VL位居第二，是视觉理解领域中的全球开源冠军；同时，Qwen3-VL还斩获纯文本赛道（Text Arena）的开源第一（全球第8），成为首个揽获纯文本和视觉两大领域同时开源第一的大模型。在Vision Arena中Qwen3-VL位居第二（图源：Qwen）并且，Qwen3-VL还在全球知名的大模型API三方聚合平台OpenRouter图像处理榜单上以48%的市场份额跃升至全球第一。Qwen3-VL在OpenRouter图像处理榜单上表现（图源：OpenRouter）近期，阿里还推出Qwen3-VL Cookbook（使用指南），涵盖图像思维、计算机使用Agent、多模态变成、3D定位、空间推理、视频理解等多种多模态用例，助用户高效上手和深度应用。","kind":"news","is_publish_news":true,"is_publish_highlight":false,"is_publish_live":false,"is_publish_wemedia":null,"editions":null,"column":"","sentiment":"0","news_tag":"","news_rank":0,"symbols":[],"gpt_button":0,"need_auth":false,"code":"91000000","status":"200"},"commentList":[],"isCommentEnd":true,"newsSizeData":{"likeSize":0,"commentSize":0,"repostSize":0,"favoriteSize":0,"likeStatus":false,"favoriteStatus":false},"APP":{"userAgent":"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)","isDev":false,"isTTM":false,"deviceId":"web-server-community-laohu8-v3","version":"4.35.9","shortVersion":"4.35.9","platform":"web","vendor":"web","appName":"laohu8","isIOS":false,"isAndroid":false,"isTiger":false,"isTHS":false,"isWeiXin":false,"isWeiXinMini":false,"isWeiBo":false,"isQQ":false,"isBaiduSwan":false,"isBaiduBox":false,"isDingTalk":false,"isToutiao":false,"isOnePlus":false,"isHuaWei":false,"isXiaomi":false,"isXiaomiWebView":false,"isOppo":false,"isVivo":false,"isSamsung":false,"isMobile":false},"href":"/m/news/2575272484","isCrawlerRequest":true}