蚂蚁百灵开源 Ling-3.0-tiny 模型，支持英伟达 DGX Spark、苹果 Mac mini 部署

IT之家08-11

IT之家 8 月 11 日消息，蚂蚁百灵今天在 Hugging Face 平台开源 Ling-3.0-tiny 模型，该模型为轻量级混合推理 MoE 架构，总参数 7.9B，每 Token 激活 1.3B 参数。官方提供 BF16、FP8 和 INT4 权重版本，适配不同平台的部署需求。据介绍，Ling-3.0-tiny 主打低成本推理，采用高效混合线性架构，将 KDA（Kimi ...

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.laohunote.com/m/news/2658947608?lang=zh_CN&edition=full","thumbnail":"https://k.sinaimg.cn/n/spider20260811/362/w1440h1322/20260811/faee-e916ee9cfba9faeb6613af0ce94589d6.png/w120h90l50t1db4.jpg","is_english":false,"pubTime":"2026-08-11 17:57","share_image_url":"https://static.laohu8.com/e9f99090a1c2ed51c021029395664489","id":"2658947608","market":"us","top_or_hot":-1,"title":"蚂蚁百灵开源 Ling-3.0-tiny 模型，支持英伟达 DGX Spark、苹果 Mac mini 部署","media":"IT之家","content":"<div>\n<p>IT之家 8 月 11 日消息，蚂蚁百灵今天在 Hugging Face 平台开源 Ling-3.0-tiny 模型，该模型为轻量级混合推理 MoE 架构，总参数 7.9B，每 Token 激活 1.3B 参数。官方提供 BF16、FP8 和 INT4 权重版本，适配不同平台的部署需求。\n\n\n\n\n据介绍，Ling-3.0-tiny 主打低成本推理，采用高效混合线性架构，将 KDA（Kimi ...</p>\n\n<a href=\"https://tech.sina.cn/mobile/xp/2026-08-12/detail-inimxvum4250371.d.html?vt=4\">网页链接</a>\n\n</div>\n","source":"sina_tech","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>蚂蚁百灵开源 Ling-3.0-tiny 模型，支持英伟达 DGX Spark、苹果 Mac mini 部署</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蚂蚁百灵开源 Ling-3.0-tiny 模型，支持英伟达 DGX Spark、苹果 Mac mini 部署\n</h2>\n\n<h4 class=\"meta\">\n\n\n2026-08-11 17:57 北京时间&nbsp;&nbsp;&nbsp;<a href=https://tech.sina.cn/mobile/xp/2026-08-12/detail-inimxvum4250371.d.html?vt=4><strong>IT之家</strong></a>\n\n\n</h4>\n\n</header>\n<article>\n<div>\n<p>IT之家 8 月 11 日消息，蚂蚁百灵今天在 Hugging Face 平台开源 Ling-3.0-tiny 模型，该模型为轻量级混合推理 MoE 架构，总参数 7.9B，每 Token 激活 1.3B 参数。官方提供 BF16、FP8 和 INT4 权重版本，适配不同平台的部署需求。\n\n\n\n\n据介绍，Ling-3.0-tiny 主打低成本推理，采用高效混合线性架构，将 KDA（Kimi ...</p>\n\n<a href=\"https://tech.sina.cn/mobile/xp/2026-08-12/detail-inimxvum4250371.d.html?vt=4\">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":"06688","symbol_name":"蚂蚁集团","start_time":0,"source_url":"https://tech.sina.cn/mobile/xp/2026-08-12/detail-inimxvum4250371.d.html?vt=4","article_id":"2658947608","we_media_id":null,"thumbnails":["https://k.sinaimg.cn/n/spider20260811/362/w1440h1322/20260811/faee-e916ee9cfba9faeb6613af0ce94589d6.png/w120h90l50t1db4.jpg"],"rights":{"source":"sina_tech","url":"https://tech.sina.cn/mobile/xp/2026-08-12/detail-inimxvum4250371.d.html?vt=4","rn_cache_url":null,"customStyle":"body{padding-top:10px;}.art_tit_h1{#titleStyle#}a{#lv2TextColor#}.art_time, .art_cite{#sourceStyle#;} .art_cite{margin-left: 3px;}.weibo_user{#sourceStyle#; margin-bottom: 0; display: inline-block;}.weibo_time{#sourceStyle#};","selectors":".module-article, article","filters":"header, .voice2, .tags, #norm_qrcode_link_auto, .unfold-box, .action, .j_float_wbro, .j_article_wbreco","directOrigin":true},"url":"https://stock-news.laohu8.com/highlight/detail?id=2658947608","pubTimestamp":1786442247,"columns":[],"sourceInfo":{"source_id":"sina_tech","name":"新浪科技"},"weMediaInfo":null,"summary":"IT之家 8 月 11 日消息，蚂蚁百灵今天在 Hugging Face 平台开源 Ling-3.0-tiny 模型，该模型为轻量级混合推理 MoE 架构，总参数 7.9B，每 Token 激活 1.3B 参数。官方提供 BF16、FP8 和 INT4 权重版本，适配不同平台的部署需求。据介绍，Ling-3.0-tiny 主打低成本推理，采用高效混合线性架构，将 KDA和 MLA按照 3:1 比例交替堆叠。IT之家注意到，该模型支持快速响应模式和多步骤推理模式，专为本地部署设计，官方已在英伟达 DGX Spark、Apple Silicon MacBook 和 Mac mini 等电脑验证。","collect":0,"end_time":0,"defaultTopTitle":"sina.cn","property":[],"viewcount":null,"language":"zh","relate_stocks":{"06688":"蚂蚁集团"},"translate_title":"Ant Braun Open Source Ling-3.0-tiny Model, Supports Nvidia DGX Spark, Apple Mac mini Deployment","themeId":null,"isJumpTheme":false,"ttsUrl":null,"symbols_score_info":{"06688":1.89},"content_text":"IT之家 8 月 11 日消息，蚂蚁百灵今天在 Hugging Face 平台开源 Ling-3.0-tiny 模型，该模型为轻量级混合推理 MoE 架构，总参数 7.9B，每 Token 激活 1.3B 参数。官方提供 BF16、FP8 和 INT4 权重版本，适配不同平台的部署需求。\n\n\n\n\n据介绍，Ling-3.0-tiny 主打低成本推理，采用高效混合线性架构，将 KDA（Kimi Delta Attention）和 MLA（Multi-Head Latent Attention，多头潜在注意力）按照 3:1 比例交替堆叠。采用包含 128 个路由专家（routed experts）的稀疏 MoE 前馈网络（FFN），在上下文处理能力和计算成本间取得平衡。IT之家注意到，该模型支持快速响应模式和多步骤推理模式，专为本地部署设计，官方已在英伟达 DGX Spark、Apple Silicon MacBook 和 Mac mini 等电脑验证。在 M4 Pro 的 MacBook 上可达到约 86-90 Token/s 的推理速度，8K 上下文长度下，峰值内存占用约为 8.34 GiB。","kind":"news","is_publish_news":true,"is_publish_highlight":false,"is_publish_live":false,"is_publish_wemedia":false,"editions":null,"column":"","sentiment":"0","news_tag":"productRelease","news_rank":0,"isVideo":false,"video":null,"symbols":[],"gpt_button":1,"need_auth":false,"need_login_tip":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,"isLaohu8Offline":false,"tenantId":"TBCN","deviceId":"web-server-community-laohu8-v3","version":"4.44.1","shortVersion":"4.44.1","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/2658947608","isCrawlerRequest":true}