Alibaba launches Qwen3.6-27B, an open-weight dense model with 27B parameters, saying it surpasses Qwen3.5-397B-A17B on major coding benchmarks (Qwen)

Techmeme ·

Alibaba releases Qwen3.6-27B, an open-weight dense model that claims to outperform the larger MoE Qwen3.5-397B-A17B on major coding benchmarks.

Categories: Model Releases, OSS & Tools

Excerpt

<a href="https://qwen.ai/blog?id=qwen3.6-27b"><img align="RIGHT" border="0" hspace="4" src="http://www.techmeme.com/260422/i48.jpg" vspace="4" /></a> <p><a href="http://www.techmeme.com/260422/p48#a260422p48" title="Techmeme permalink"><img height="12" src="http://www.techmeme.com/img/pml.png" style="border: none; padding: 0; margin: 0;" width="11" /></a> <a href="https://qwen.ai/">Qwen</a>:<br /> <span style="font-size: 1.3em;"><b><a href="https://qwen.ai/blog?id=qwen3.6-27b">Alibaba launches Qwen3.6-27B, an open-weight dense model with 27B parameters, saying it surpasses Qwen3.5-397B-A17B on major coding benchmarks</a></b></span>&nbsp; &mdash;&nbsp; &middot; 4226 words&nbsp; &middot; QwenTeam&#20008;Translations:.&#20307;&#20013;&#25991;&nbsp; &mdash;&nbsp; HUGGING FACE&nbsp; &mdash;&nbsp; MODELSCOPE&nbsp; &mdash;&nbsp; DISCORD</p>

Read at source: http://www.techmeme.com/260422/p48#a260422p48