https://zml.ai/tags/laguna/ Recent content in Laguna on ZML - Model to Metal Hugo en-us Tue, 21 Jul 2026 19:00:00 +0100 https://zml.ai/posts/laguna-s-2-1/ Tue, 21 Jul 2026 19:00:00 +0100 https://zml.ai/posts/laguna-s-2-1/ <p>In close collaboration with <a href="https://poolside.ai/">Poolside</a>, we&rsquo;re happy to announce the support of <a href="https://poolside.ai/blog/introducing-laguna-s-2-1">Laguna S 2.1</a>, their new open-weight model for agentic coding and long-horizon work.</p> <p>It is a <strong>118B total parameters</strong> Mixture-of-Experts model with <strong>8B activated parameters</strong> per token and supports a context window of up to <strong>1M tokens</strong>, available in <strong>thinking</strong> and <strong>no-thinking</strong> modes.</p> <p>And it&rsquo;s <strong>available today</strong> in ZML/LLMD <strong>with DFlash support</strong>. Most importantly (and as always with us), it&rsquo;s available on all the supported platforms: <strong>NVIDIA</strong>, <strong>AMD</strong>, <strong>Intel</strong>, <strong>Google TPU</strong> and <strong>Apple Metal</strong>.</p>