{"id":58181,"date":"2026-09-20T09:30:11","date_gmt":"2026-09-20T01:30:11","guid":{"rendered":"https:\/\/www.1ai.net\/?p=58181"},"modified":"2026-09-20T09:30:11","modified_gmt":"2026-09-20T01:30:11","slug":"%e4%b8%ad%e5%9b%bd%e7%94%b5%e4%bf%a1%e5%bc%80%e6%ba%90%e9%a6%96%e4%b8%aa%e5%85%a8%e6%a0%88%e5%9b%bd%e4%ba%a7%e8%bd%bb%e9%87%8f%e7%ba%a7%e6%99%ba%e8%83%bd%e4%bd%93%e5%a4%a7%e6%a8%a1%e5%9e%8b-xing4-0-29","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/58181.html","title":{"rendered":"China Telecommunications Open Source ' s first large-scale lightweight intelligence model for all-in-country production Xing4.0-29B-A4B"},"content":{"rendered":"<p>The news of September 20th<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e4%b8%ad%e5%9b%bd%e7%94%b5%e4%bf%a1\" title=\"[View articles tagged with [China Telecom]]\" target=\"_blank\" >China Telecom<\/a>A new generation of stars was launched on September 17th<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%a4%a7%e6%a8%a1%e5%9e%8b\" title=\"[View articles tagged with [large models]]\" target=\"_blank\" >Large Model<\/a> Xing4.0-29B-A4B, the total size of the model 29B, activating only 4B, original support 256K context, extended to 512K<strong>The country ' s first large-scale model of 10 billion parameters to optimize the depth of complex engineering tasks, based on the country ' s economic capacity and the national framework<\/strong>.<\/p>\n<p>Officially, from training chips to reasoning deployment<strong>It's all Chinese<\/strong>\u00a0- Training, adaptation of the national production framework, self-study structures<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%bc%80%e6%ba%90\" title=\"[View articles tagged with [open source]]\" target=\"_blank\" >Open Source<\/a>Eco, one way through\u3002<\/p>\n<p>According to the SuperCLUE assessment, in terms of intelligence capabilities, Xing4.0-29B-A4B scored 93.52, ranked third, and the gap with both head Qwen models was less than one point\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-58182\" title=\"19150ad1jln2sv000sd000ms00e9m\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2026\/09\/19150ad1j00tln2sv000sd000ms00e9m.jpg\" alt=\"19150ad1jln2sv000sd000ms00e9m\" width=\"820\" height=\"513\" \/><\/p>\n<p>It is described that Xing4.0-29B-A4B can be reduced to 15GB (approximately 75% compared to FP16), RTX 3090, RTX 4090, a consumption scale of 24G, by quantifying 4-bit, to enable local context missions\u3002<\/p>\n<p>Xing4.0-29B-A4B Open source routes for the continuation of the Big Star Model provide full compatibility with mainstream open source ecology: support for fine-tuning structures such as LLAMA-Factory, MindFormers; fit for mainstream reasoning frameworks such as SGLang, vLM, KTransformers; and the Agent Framework provides orientation adaptations to OpenCode, Claude Code, OpenClaw, Hermes and deep alignment of framework formats\u3002<\/p>\n<p>Xing4.0-29B-A4B, an open-source community, 1AI with relevant links:<\/p>\n<ul>\n<li>HuggingFace: https:\/\/huggingface.co\/XingChen-AGI\/Xing4.0-29B-A4B<\/li>\n<li>GitHub: https:\/\/github.com\/XingChen-AGI\/Xing4.0-29B-A4B<\/li>\n<li>Magic: https:\/\/modelsscope.cn\/models\/XingChen-AGI\/Xing4.0-29B-A4B<\/li>\n<li>Gitee: https:\/\/gitee.com\/xingchen-agi\/xing4.0-29b-a4b<\/li>\n<li>Magic: https:\/\/moders.cn\/models\/XingChen-AGI\/Xing4.0-29B-A4B<\/li>\n<\/ul>","protected":false},"excerpt":{"rendered":"<p>On September 20, Chinese telecommunications released on September 17, a new-generation star-size model, Xing4.0-29B-A4B, with a total of 29B, a activation parameter of only 4B, with original support of 256K in the context, which can be extended to 512K, the first large-scale model in the country to optimize the depth of complex engineering tasks based on national capacity and framework. Officially, from training chips to reasoning deployment, the whole of the country's production \u2014 training, adaptation of the national production framework, self-study structures, open-source ecology \u2014 is one route. According to the SuperCLUE assessment, in terms of intelligence capabilities, Xing4.0-29B-A4B score 93.52, ranked third, and two headers<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[3419,216,219],"collection":[],"class_list":["post-58181","post","type-post","status-publish","format-standard","hentry","category-news","tag-3419","tag-216","tag-219"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/58181","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=58181"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/58181\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=58181"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=58181"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=58181"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=58181"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}