阿里巴巴发布了其 Qwen3.6-27B 模型，这是一个开源的、稠密的模型，在编码方面表现强劲，在关键基准测试中超越了规模大得多的前代模型。该新模型原生支持多模态，能够处理视觉和语言输入。此次发布伴随着与 vLLM 和 SGLang 等流行 AI 工具的快速集成，实现了本地执行和更广泛的可访问性。 AI
排序理由 发布了具有性能声明和基准测试结果的开源模型。
AI 生成摘要 · Google Gemini · 来自 12 个来源。 我们如何撰写摘要 →
阿里巴巴的 Qwen3.6 模型在编码和多模态方面表现强劲
报道来源 [12]
-
⚡️⚡️在本地运行 Qwen3.6-27B！@UnslothAI
⚡️⚡️Run Qwen3.6-27B locally! @UnslothAI
-
Day 0 vLLM 支持 Qwen3.6-27B！ @vllm_project ♥️❤️
Day 0 vLLM support for Qwen3.6-27B! @vllm_project ♥️❤️
-
感谢 @lmsysorg！现在就在 SGLang 上试试吧！🚀🚀
Thanks to @lmsysorg ！ Try it on SGLang now!🚀🚀
-
VLM 性能：Qwen3.6-27B 原生多模态，单一统一检查点支持视觉语言推理和非推理模式——与...相同
VLM Performance：Qwen3.6-27B is natively multimodal, supporting both vision-language thinking and non-thinking modes in a single unified checkpoint — the same as Qwen3.6-35B-A3B. It handles images and video alongside text, enabling multimodal reasoning, document understanding, htt…
-
LM 性能：仅用 27B 参数，Qwen3.6-27B 在所有主要编码基准测试中均优于 Qwen3.5-397B-A17B（总计 397B / 活跃 17B，规模大约 15 倍！）——
LM Performance：With only 27B parameters, Qwen3.6-27B outperforms the Qwen3.5-397B-A17B (397B total / 17B active, ~15x larger!) on every major coding benchmark — including SWE-bench Verified (77.2 vs. 76.2), SWE-bench Pro (53.5 vs. 50.9), Terminal-Bench 2.0 (59.3 vs. 52.5), and ht…
-
🚀 隆重推出 Qwen3.6-27B，我们最新推出的密集型、开源模型，具备旗舰级编码能力！
🚀 Meet Qwen3.6-27B, our latest dense, open-source model, packing flagship-level coding power! Yes, 27B, and Qwen3.6-27B punches way above its weight. 👇 What's new: 🧠 Outstanding agentic coding — surpasses Qwen3.5-397B-A17B across all major coding benchmarks 💡 Strong https://t.c…
-
VLM 性能：Qwen3.6 原生多模态，Qwen3.6-35B-A3B 展示的感知和多模态推理能力远超其规模所能达到的水平
VLM Performance：Qwen3.6 is natively multimodal, and Qwen3.6-35B-A3B showcases perception and multimodal reasoning capabilities that far exceed what its size would suggest, with only around 3 billion activated parameters. Across most vision-language benchmarks, its performance htt…
-
LM性能：Qwen3.6-35B-A3B在多项关键编码基准测试中超越了密集型27B参数的Qwen3.5-27B，并显著超越了其直接前代产品Qw
LM Performance：Qwen3.6-35B-A3B outperforms the dense 27B-param Qwen3.5-27B on several key coding benchmarks and dramatically surpasses its direct predecessor Qwen3.5-35B-A3B, especially on agentic coding and reasoning tasks. https://t.co/PyXDNruoy2
-
⚡ 认识 Qwen3.6-35B-A3B：现已开源！🚀🚀
⚡ Meet Qwen3.6-35B-A3B：Now Open-Source！🚀🚀 A sparse MoE model, 35B total params, 3B active. Apache 2.0 license. 🔥 Agentic coding on par with models 10x its active size 📷 Strong multimodal perception and reasoning ability 🧠 Multimodal thinking + non-thinking modes https://t.co/UM…
-
终于来了！🚀 非常感谢 @opencode 团队的无缝集成。Qwen3.6-Plus 和 Qwen3.5-Plus 现已在 Go 中上线！
It’s finally here! 🚀 Huge thanks to the @opencode team for the seamless integration. Qwen3.6-Plus and Qwen3.5-Plus are now live in Go! Update now to try it out! 👇
-
（更多 Linux 和 FOSS 新闻请见本帖之前的帖子）Qwen3.6-27B 开源 27B 稠密模型超越了之前的编码基准：https:// alternativeto.net/
(more Linux and FOSS news in previous posts of thread) Qwen3.6-27B open-source 27B dense model surpasses previous coding benchmarks: https:// alternativeto.net/news/2026/4/ qwen3-6-27b-open-source-27b-dense-model-surpasses-previous-coding-benchmarks/ Chinese AI lab DeepSeek has r…
链接 phoronix.com -
🧠 Qwen Code v0.15.0 增加跨会话记忆 跨会话记忆、批量多文件操作、钩子扩展和后台子代理改进了更长的代理工作流
🧠 Qwen Code v0.15.0 adds cross-session memory Cross-session memory, batch multi-file ops, hook expansion, and background subagents improve longer agent workflows. solomonneas.dev/intel # AI # ML # AgenticAI # DevTools