poolside 新出的 Laguna S 2.1 开源又高效，118B 模型只激活 8B 就能跑，还支持 1M 上下文，值得一试。
poolsideai 发布了最新开源模型 Laguna S 2.1，总参数量 118B，采用 MoE 架构，每个 token 仅激活 8B 参数。该模型支持 1M token 上下文窗口，并提供思考与免思考两种模式。权重已在 Hugging Face 以 OpenMDW-1.1 许可证开放，可在单台 NVIDIA DGX Spark 上本地运行。Laguna S 2.1 在性能上可与参数量大数倍的模型竞争。
Congrats to the @poolsideai team on their latest release, Laguna S 2.1. It’s open-weight, delivers ...
Congrats to the @poolsideai team on their latest release, Laguna S 2.1. It’s open-weight, delivers way beyond its size, runs great locally and you can customize it with NVIDIA NeMo. Go try it out on @OpenRouter or download from @huggingface � huggingface.co/poolside/Lagun… O Poolside @poolsideai Today we're releasing Laguna S 2.1, our most capable model to date. It's a 118B total parameter Mixture-of-Experts model with 8B activated per token, a context window of up to 1M tokens, and thinking and no-thinking modes. Capable enough to hold its own against models many times its size. Small enough to run on a single @NVIDIAAI DGX Spark. Laguna S 2.1 is fully open under OpenMDW-1.1, with weights available today on @huggingface poolside.ai/blog/introduci… Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 3 🔄 11 ❤️ 66 👀 5083 📊 10 ⚡