Agents
Thanks to @lmsysorg οΌ Try it on SGLang now!ππ
Thanks to @lmsysorg οΌ Try it on SGLang now!ππ π Qwen3.6-27B is here, and we have day 0 support on SGLang β 27B params, beats Qwen3.5-397B-A17B across major coding benchmarks β Agentic coding β Text +
Thanks to @lmsysorg οΌ Try it on SGLang now!ππ π Qwen3.6-27B is here, and we have day 0 support on SGLang β 27B params, beats Qwen3.5-397B-A17B across major coding benchmarks β Agentic coding β Text + multimodal reasoning β Thinking / non-thinking modes Smaller model. Bigger results. Try it on SGLang now π₯
Related
- LM PerformanceοΌQwen3.6-35B-A3B outperforms the dense 27B-param Qwen3.5-27B on several key coding benchmarks and dramatically surpasses its dβ¦
- Sub-agent Model Selection β Different Tasks, Different Models Your main agent runs Qwen3.6-Plus for quality. But not every subtask needs a fβ¦
- Agentic Infrastructure
- Kimi K2.6 just entered the chat. > beats gpt 5.4 and opus 4.6 on coding. > open source. open weight. > 3x-5x cheaper. > really good for peopβ¦
- GLM-5.1 is now available in Windsurf! Try it out and let us know what you think
Source: Qwen (X) | 2026-04-23