Qwen3.8-27B开源了，SGLang当天就能跑，单张5090能到206 tok/s，小模型之王回来了，试试吧。
阿里开源Qwen3.8-27B，SGLang团队当天完成适配。在单张RTX 5090上，借助NVFP4和DSpark优化，解码速度达到206.1 tok/s。在DGX Spark上解码速度为38.28 tok/s。该模型在智能体规划和长时任务上表现突出。
Yes, we are back👑, with 206 tok/s on a single RTX 5090! Amazing Day-0 work from the SGLang team. Gi...
Yes, we are back👑, with 206 tok/s on a single RTX 5090! Amazing Day-0 work from the SGLang team. Give it a try~ @sgl_project SGLang @sgl_project The king of small models is back! Qwen3.8-27B from @Alibaba_Qwen is open source, and Day-0 support is live in SGLang: - 206.1 tok/s decode on a single RTX 5090, with our NVFP4 plus DSpark - 38.28 tok/s decode on DGX Spark Qwen3.8-27B raises the bar again for what a small model can do on agentic planning and long-horizon tasks. Long live the (small model) king! Run it locally with SGLang 👇 Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 9 🔄 9 ❤️ 113 👀 5217 📊 17 ⚡
- IT之家15:13原文