Poolside的Laguna S 2.1是个118B参数的稀疏MoE模型，只激活8B参数，SWE-bench多语言拿下78.5%，还能跑在单个DGX Spark上，适合长时编程任务。
Poolside发布Laguna S 2.1模型，总参数量118B，采用稀疏MoE架构，每token仅激活8B参数。模型支持1M上下文窗口，提供思考与非思考两种模式。在Terminal-Bench 2.1上获得70.2%准确率，在SWE-bench Multilingual上达78.5%。官方NVFP4量化版本可运行于单个NVIDIA DGX Spark。模型已在SGLang框架上提供Day-0支持。
🎉 Day-0 support for Laguna S 2.1 from @poolsideai …
🎉 Day-0 support for Laguna S 2.1 from @poolsideai is now live on SGLang! 118B total params, 1M context, with thinking & no-thinking modes.
✅ Long-horizon persistence: keeps planning, testing, and self-correcting up to ~24h runs with little intervention ✅ Built for agentic coding: 70.2% Terminal-Bench 2.1, 78.5% SWE-bench Multilingual ✅ Sparse MoE efficiency: only 8B active params per token, making long agent runs and RL loops fast and cheap ✅ Runs locally: official NVFP4 quantization fits on a single NVIDIA DGX Spark
Cookbook: https://t.co/HYxMBPIv4E
Run it now with SGLang!