[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-qwen-3-6-35b-a3b-open-source-coding-262k":3,"news-related-97a4f24e-c65b-4e95-b9ed-b05997d88af2":34},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":26,"news_slug":27,"published_at":28,"created_at":29,"modified_at":30,"is_published":31,"publish_type":32,"image_url":13,"view_count":33},"97a4f24e-c65b-4e95-b9ed-b05997d88af2","Qwen3.6-35B-A3B发布：开源大模型的效率革命","阿里云通义千问团队近日发布了Qwen3.6系列的首个开放权重变体Qwen3.6-35B-A3B，这一新版本在保持强大的编程能力基础上，重点优化了稳定性和实际应用体验。作为继Qwen3.5之后的重大升级，Qwen3.6-35B-A3B采用了社区直接反馈驱动的开发模式，优先考虑开发者的实际需求。最引人注目的是其高达262,144 tokens的超长上下文窗口，这意味着模型能够处理更长的代码文件和复杂的文档分析场景。在技术架构上，该模型与多种主流推理框架深度兼容，包括vLLM、SGLang和KTransformers等，为不同规模的应用部署提供了灵活选择。特别值得一提的是，SGLang框架下的部署方案支持工具使用和多令牌预测功能，进一步提升了开发效率。Qwen3.6-35B-A3B的发布标志着开源大模型在实用性和性能上的又一次突破。它不仅证明了开源模型在特定任务上能够媲美甚至超越闭源方案，更重要的是展示了大模型从实验室走向实际应用的关键转变——从追求参数规模到注重稳定性和用户体验。随着更多企业级应用的落地，这类注重实际价值的开源模型将推动AI技术民主化进程，让更多开发者和企业能够负担得起高质量的大模型服务。这不仅是一场技术竞赛，更是AI生态系统健康发展的重要一步。","https:\u002F\u002Fhuggingface.co\u002FQwen\u002FQwen3.6-35B-A3B","24d5c6c5-6573-4180-a1fd-f1459842d1af",[10,14,17,20,23],{"id":11,"name":12,"slug":12,"description":13,"color":13},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",{"id":18,"name":19,"slug":19,"description":13,"color":13},"7e89b5cc-57db-4f37-bc6d-28919a73931c","model-release",{"id":21,"name":22,"slug":22,"description":13,"color":13},"b1853a5a-d940-42b7-94f9-0488ee3f2cf7","new-model",{"id":24,"name":25,"slug":25,"description":13,"color":13},"b9bd9039-fcdb-41a8-b85b-fc1587def2b9","open-source",[],"qwen-3-6-35b-a3b-open-source-coding-262k","2026-04-25T02:05:00Z","2026-04-25T10:06:33.241539Z","2026-08-19T02:08:40.142862Z",true,"agent",132,{"items":35},[36,41,46,51,56,61],{"id":37,"title":38,"news_slug":39,"published_at":40},"5878a668-282c-4b88-b2b8-7eef40b7938c","LFM2.5-2.6B：2.5GB 内存跑本机 Agent 220 tok\u002Fs","lfm2-5-2-6b-on-device-agent","2026-08-11T00:00:00+00:00",{"id":42,"title":43,"news_slug":44,"published_at":45},"06651fbd-69a7-42b7-adac-68fc5db5063e","Soofi S 30B 用 MoE + 混合架构挤进完全开源头名:德国把主权 AI 写进 3.2B 激活参数","soofi-s-30b-sovereign","2026-07-13T20:04:00+00:00",{"id":47,"title":48,"news_slug":49,"published_at":50},"222d6fbf-e9bc-4d63-8481-88ea28fd499c","Sber GigaChat 3.5 Ultra 开源：线性注意力 MoE 把长文本速度拉高 4 倍、模型尺寸砍半","sber-gigachat-3-5-ultra","2026-07-10T18:05:00+00:00",{"id":52,"title":53,"news_slug":54,"published_at":55},"d0d290cd-c169-495c-b0be-b559caa6eaa0","Grok 4.5 公众开放定档 7月9日:Musk 押注的不是参数,而是「Opus 级但更便宜」","grok-4-5-public-launch","2026-07-08T12:30:00+00:00",{"id":57,"title":58,"news_slug":59,"published_at":60},"1d80585e-c797-4aa1-ac68-ef87334d5d0c","PLaMo 3.0 Prime 正式发布：PFN 把「日语实战」做成日本国产 LLM 的差异化战场","plamo-3-0-prime-pfn-japanese-domestic","2026-06-24T08:15:00+00:00",{"id":62,"title":63,"news_slug":64,"published_at":65},"31259851-c64e-47dd-99cf-bcfae698b14f","LFM2.5-Retrievers：Liquid AI 把 LFM「单向」改成「双向 350M」，11 语种检索刷 SOTA","lfm-2-5-retrievers-liquid-350m-bidirectional","2026-06-22T03:30:00+00:00"]