{
  "@context": "https://schema.org",
  "@id": "https://aggr.aymericbeaumet.com/items/zml-ai/2026-07-21-laguna-s-2-1/#webpage",
  "@type": [
    "WebPage",
    "ArchiveComponent"
  ],
  "articleBody": "[ZML - Model to Metal](https://zml.ai/)\n\n- [Blog](https://zml.ai/posts/)\n- [LLMD](https://zml.ai/llmd/)\n- [GitHub 3.5K](https://github.com/zml/zml)\n- [Docs](https://github.com/zml/zml/tree/master/docs)\n- [Discord](https://discord.com/invite/puhdWt8gzZ)\n- [Contact](https://zml.ai/cdn-cgi/l/email-protection#e088858c8c8fa09a8d8cce8189)\n\n[Back to posts](https://zml.ai/posts/)\n\nArticle\n\nPoolside's open-weight model for agentic coding and long-horizon work.\n\nJuly 21, 2026 inference / performance / NVIDIA / AMD / TPU / Intel / Apple / Metal / poolside / laguna\n\nIn close collaboration with [Poolside](https://poolside.ai/), we’re happy to announce the support of [Laguna S 2.1](https://poolside.ai/blog/introducing-laguna-s-2-1), their new open-weight model for agentic coding and long-horizon work.\n\nIt is a **118B total parameters** Mixture-of-Experts model with **8B activated parameters** per token and supports a context window of up to **1M tokens**, available in **thinking** and **no-thinking** modes.\n\nAnd it’s **available today** in ZML/LLMD **with DFlash support**. Most importantly (and as always with us), it’s available on all the supported platforms: **NVIDIA**, **AMD**, **Intel**, **Google TPU** and **Apple Metal**.\n\n## Run it today\n\n**NVIDIA**\n\n```bash\ndocker run -p 8000:8000 --shm-size=256GB --gpus=all -e HF_TOKEN -it zmlai/llmd:cuda \\\n    --model=hf://poolside/Laguna-S-2.1 \\\n    --dflash-model=hf://poolside/Laguna-S-2.1-DFlash\n```\n\n**AMD**\n\n```bash\ndocker run -p 8000:8000 --shm-size=256GB --device=/dev/kfd --device=/dev/dri -e HF_TOKEN -it zmlai/llmd:rocm \\\n    --model=hf://poolside/Laguna-S-2.1 \\\n    --dflash-model=hf://poolside/Laguna-S-2.1-DFlash\n```\n\n**Intel**\n\n```bash\ndocker run -p 8000:8000 --device=/dev/dri -e HF_TOKEN -it zmlai/llmd:oneapi \\\n    --model=hf://poolside/Laguna-S-2.1 \\\n    --dflash-model=hf://poolside/Laguna-S-2.1-DFlash\n```\n\n**Google TPU**\n\n```bash\ndocker run --net=host --privileged -e HF_TOKEN -it zmlai/llmd:tpu \\\n    --model=hf://poolside/Laguna-S-2.1 \\\n    --dflash-model=hf://poolside/Laguna-S-2.1-DFlash\n```\n\n**Apple Metal**\n\n```bash\nbrew install zml/zml/llmd\nllmd --model=hf://poolside/Laguna-S-2.1 --dflash-model=hf://poolside/Laguna-S-2.1-DFlash\n```\n\n## Benchmarks\n\n*It’s a good model, sir.*\n\n![](https://zml.ai/posts/laguna-s-2-1/laguna-s-2-1-chart.svg)\n",
  "authors": [],
  "captured_at": "2026-09-08T10:17:10.166315+00:00",
  "category": "ai",
  "content_html": "<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://zml.ai/\">ZML - Model to Metal</a></p>\n<ul>\n<li><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://zml.ai/posts/\">Blog</a></li>\n<li><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://zml.ai/llmd/\">LLMD</a></li>\n<li><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/zml/zml\">GitHub 3.5K</a></li>\n<li><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/zml/zml/tree/master/docs\">Docs</a></li>\n<li><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://discord.com/invite/puhdWt8gzZ\">Discord</a></li>\n<li><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://zml.ai/cdn-cgi/l/email-protection#e088858c8c8fa09a8d8cce8189\">Contact</a></li>\n</ul>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://zml.ai/posts/\">Back to posts</a></p>\n<p>Article</p>\n<p>Poolside's open-weight model for agentic coding and long-horizon work.</p>\n<p>July 21, 2026 inference / performance / NVIDIA / AMD / TPU / Intel / Apple / Metal / poolside / laguna</p>\n<p>In close collaboration with <a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://poolside.ai/\">Poolside</a>, we’re happy to announce the support of <a target=\"_blank\" rel=\"noopener noreferrer\" 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>\n<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>\n<p>And it’s <strong>available today</strong> in ZML/LLMD <strong>with DFlash support</strong>. Most importantly (and as always with us), it’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>\n<h2>Run it today</h2>\n<p><strong>NVIDIA</strong></p>\n<pre><code class=\"language-bash\"><span class=\"code-snippet\" data-language=\"Shell\"><span class=\"syntax-source syntax-shell syntax-bash\"><span class=\"syntax-meta syntax-function-call syntax-shell\"><span class=\"syntax-variable syntax-function syntax-shell\">docker</span></span><span class=\"syntax-meta syntax-function-call syntax-arguments syntax-shell\"> run<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> -</span>p</span> 8000:8000<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> --</span>shm-size</span><span class=\"syntax-keyword syntax-operator syntax-assignment syntax-option syntax-shell\">=</span>256GB<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> --</span>gpus</span><span class=\"syntax-keyword syntax-operator syntax-assignment syntax-option syntax-shell\">=</span>all<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> -</span>e</span> HF_TOKEN<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> -</span>it</span> zmlai/llmd:cuda <span class=\"syntax-punctuation syntax-separator syntax-continuation syntax-line syntax-shell\">\\\n</span><span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\">    --</span>model</span><span class=\"syntax-keyword syntax-operator syntax-assignment syntax-option syntax-shell\">=</span>hf://poolside/Laguna-S-2.1 <span class=\"syntax-punctuation syntax-separator syntax-continuation syntax-line syntax-shell\">\\\n</span><span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\">    --</span>dflash-model</span><span class=\"syntax-keyword syntax-operator syntax-assignment syntax-option syntax-shell\">=</span>hf://poolside/Laguna-S-2.1-DFlash</span>\n</span></span></code></pre>\n<p><strong>AMD</strong></p>\n<pre><code class=\"language-bash\"><span class=\"code-snippet\" data-language=\"Shell\"><span class=\"syntax-source syntax-shell syntax-bash\"><span class=\"syntax-meta syntax-function-call syntax-shell\"><span class=\"syntax-variable syntax-function syntax-shell\">docker</span></span><span class=\"syntax-meta syntax-function-call syntax-arguments syntax-shell\"> run<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> -</span>p</span> 8000:8000<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> --</span>shm-size</span><span class=\"syntax-keyword syntax-operator syntax-assignment syntax-option syntax-shell\">=</span>256GB<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> --</span>device</span><span class=\"syntax-keyword syntax-operator syntax-assignment syntax-option syntax-shell\">=</span>/dev/kfd<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> --</span>device</span><span class=\"syntax-keyword syntax-operator syntax-assignment syntax-option syntax-shell\">=</span>/dev/dri<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> -</span>e</span> HF_TOKEN<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> -</span>it</span> zmlai/llmd:rocm <span class=\"syntax-punctuation syntax-separator syntax-continuation syntax-line syntax-shell\">\\\n</span><span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\">    --</span>model</span><span class=\"syntax-keyword syntax-operator syntax-assignment syntax-option syntax-shell\">=</span>hf://poolside/Laguna-S-2.1 <span class=\"syntax-punctuation syntax-separator syntax-continuation syntax-line syntax-shell\">\\\n</span><span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\">    --</span>dflash-model</span><span class=\"syntax-keyword syntax-operator syntax-assignment syntax-option syntax-shell\">=</span>hf://poolside/Laguna-S-2.1-DFlash</span>\n</span></span></code></pre>\n<p><strong>Intel</strong></p>\n<pre><code class=\"language-bash\"><span class=\"code-snippet\" data-language=\"Shell\"><span class=\"syntax-source syntax-shell syntax-bash\"><span class=\"syntax-meta syntax-function-call syntax-shell\"><span class=\"syntax-variable syntax-function syntax-shell\">docker</span></span><span class=\"syntax-meta syntax-function-call syntax-arguments syntax-shell\"> run<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> -</span>p</span> 8000:8000<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> --</span>device</span><span class=\"syntax-keyword syntax-operator syntax-assignment syntax-option syntax-shell\">=</span>/dev/dri<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> -</span>e</span> HF_TOKEN<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> -</span>it</span> zmlai/llmd:oneapi <span class=\"syntax-punctuation syntax-separator syntax-continuation syntax-line syntax-shell\">\\\n</span><span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\">    --</span>model</span><span class=\"syntax-keyword syntax-operator syntax-assignment syntax-option syntax-shell\">=</span>hf://poolside/Laguna-S-2.1 <span class=\"syntax-punctuation syntax-separator syntax-continuation syntax-line syntax-shell\">\\\n</span><span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\">    --</span>dflash-model</span><span class=\"syntax-keyword syntax-operator syntax-assignment syntax-option syntax-shell\">=</span>hf://poolside/Laguna-S-2.1-DFlash</span>\n</span></span></code></pre>\n<p><strong>Google TPU</strong></p>\n<pre><code class=\"language-bash\"><span class=\"code-snippet\" data-language=\"Shell\"><span class=\"syntax-source syntax-shell syntax-bash\"><span class=\"syntax-meta syntax-function-call syntax-shell\"><span class=\"syntax-variable syntax-function syntax-shell\">docker</span></span><span class=\"syntax-meta syntax-function-call syntax-arguments syntax-shell\"> run<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> --</span>net</span><span class=\"syntax-keyword syntax-operator syntax-assignment syntax-option syntax-shell\">=</span>host<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> --</span>privileged</span><span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> -</span>e</span> HF_TOKEN<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> -</span>it</span> zmlai/llmd:tpu <span class=\"syntax-punctuation syntax-separator syntax-continuation syntax-line syntax-shell\">\\\n</span><span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\">    --</span>model</span><span class=\"syntax-keyword syntax-operator syntax-assignment syntax-option syntax-shell\">=</span>hf://poolside/Laguna-S-2.1 <span class=\"syntax-punctuation syntax-separator syntax-continuation syntax-line syntax-shell\">\\\n</span><span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\">    --</span>dflash-model</span><span class=\"syntax-keyword syntax-operator syntax-assignment syntax-option syntax-shell\">=</span>hf://poolside/Laguna-S-2.1-DFlash</span>\n</span></span></code></pre>\n<p><strong>Apple Metal</strong></p>\n<pre><code class=\"language-bash\"><span class=\"code-snippet\" data-language=\"Shell\"><span class=\"syntax-source syntax-shell syntax-bash\"><span class=\"syntax-meta syntax-function-call syntax-shell\"><span class=\"syntax-variable syntax-function syntax-shell\">brew</span></span><span class=\"syntax-meta syntax-function-call syntax-arguments syntax-shell\"> install zml/zml/llmd</span>\n<span class=\"syntax-meta syntax-function-call syntax-shell\"><span class=\"syntax-variable syntax-function syntax-shell\">llmd</span></span><span class=\"syntax-meta syntax-function-call syntax-arguments syntax-shell\"><span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> --</span>model</span><span class=\"syntax-keyword syntax-operator syntax-assignment syntax-option syntax-shell\">=</span>hf://poolside/Laguna-S-2.1<span class=\"syntax-variable syntax-parameter syntax-option syntax-shell\"><span class=\"syntax-punctuation syntax-definition syntax-parameter syntax-shell\"> --</span>dflash-model</span><span class=\"syntax-keyword syntax-operator syntax-assignment syntax-option syntax-shell\">=</span>hf://poolside/Laguna-S-2.1-DFlash</span>\n</span></span></code></pre>\n<h2>Benchmarks</h2>\n<p><em>It’s a good model, sir.</em></p>\n<p><picture class=\"article-picture article-picture-fallback\" style=\"--image-ratio:16 / 9\"><img src=\"https://zml.ai/posts/laguna-s-2-1/laguna-s-2-1-chart.svg\" alt=\"\" loading=\"eager\" decoding=\"async\" fetchpriority=\"high\" referrerpolicy=\"no-referrer\" class=\"progressive-image\"></picture></p>\n",
  "content_markdown": "[ZML - Model to Metal](https://zml.ai/)\n\n- [Blog](https://zml.ai/posts/)\n- [LLMD](https://zml.ai/llmd/)\n- [GitHub 3.5K](https://github.com/zml/zml)\n- [Docs](https://github.com/zml/zml/tree/master/docs)\n- [Discord](https://discord.com/invite/puhdWt8gzZ)\n- [Contact](https://zml.ai/cdn-cgi/l/email-protection#e088858c8c8fa09a8d8cce8189)\n\n[Back to posts](https://zml.ai/posts/)\n\nArticle\n\nPoolside's open-weight model for agentic coding and long-horizon work.\n\nJuly 21, 2026 inference / performance / NVIDIA / AMD / TPU / Intel / Apple / Metal / poolside / laguna\n\nIn close collaboration with [Poolside](https://poolside.ai/), we’re happy to announce the support of [Laguna S 2.1](https://poolside.ai/blog/introducing-laguna-s-2-1), their new open-weight model for agentic coding and long-horizon work.\n\nIt is a **118B total parameters** Mixture-of-Experts model with **8B activated parameters** per token and supports a context window of up to **1M tokens**, available in **thinking** and **no-thinking** modes.\n\nAnd it’s **available today** in ZML/LLMD **with DFlash support**. Most importantly (and as always with us), it’s available on all the supported platforms: **NVIDIA**, **AMD**, **Intel**, **Google TPU** and **Apple Metal**.\n\n## Run it today\n\n**NVIDIA**\n\n```bash\ndocker run -p 8000:8000 --shm-size=256GB --gpus=all -e HF_TOKEN -it zmlai/llmd:cuda \\\n    --model=hf://poolside/Laguna-S-2.1 \\\n    --dflash-model=hf://poolside/Laguna-S-2.1-DFlash\n```\n\n**AMD**\n\n```bash\ndocker run -p 8000:8000 --shm-size=256GB --device=/dev/kfd --device=/dev/dri -e HF_TOKEN -it zmlai/llmd:rocm \\\n    --model=hf://poolside/Laguna-S-2.1 \\\n    --dflash-model=hf://poolside/Laguna-S-2.1-DFlash\n```\n\n**Intel**\n\n```bash\ndocker run -p 8000:8000 --device=/dev/dri -e HF_TOKEN -it zmlai/llmd:oneapi \\\n    --model=hf://poolside/Laguna-S-2.1 \\\n    --dflash-model=hf://poolside/Laguna-S-2.1-DFlash\n```\n\n**Google TPU**\n\n```bash\ndocker run --net=host --privileged -e HF_TOKEN -it zmlai/llmd:tpu \\\n    --model=hf://poolside/Laguna-S-2.1 \\\n    --dflash-model=hf://poolside/Laguna-S-2.1-DFlash\n```\n\n**Apple Metal**\n\n```bash\nbrew install zml/zml/llmd\nllmd --model=hf://poolside/Laguna-S-2.1 --dflash-model=hf://poolside/Laguna-S-2.1-DFlash\n```\n\n## Benchmarks\n\n*It’s a good model, sir.*\n\n![](https://zml.ai/posts/laguna-s-2-1/laguna-s-2-1-chart.svg)\n",
  "dateCreated": "2026-09-08T10:17:10.166315+00:00",
  "date_created": "2026-07-21T18:00:00+00:00",
  "date_modified": "2026-07-21T18:00:00+00:00",
  "date_published": "2026-07-21T18:00:00+00:00",
  "description": "In close collaboration with Poolside, we’re happy to announce the support of Laguna S 2.1, their new open-weight model for agentic coding and long-horizon work. It is a 118B total parameters Mixture-of-Experts model with 8B activated…",
  "external_url": "https://zml.ai/posts/laguna-s-2-1/",
  "git": {
    "commit": "ebb0941c5c06a2ab2377342d607535262a3e969e",
    "path": "items/zml-ai/2026/07/2026-07-21-laguna-s-2-1.md",
    "permalink": "https://github.com/aymericbeaumet/aggr-instance/blob/ebb0941c5c06a2ab2377342d607535262a3e969e/items/zml-ai/2026/07/2026-07-21-laguna-s-2-1.md"
  },
  "id": "urn:aggr:item:a6771074693fd7bb1c084fde86d40cd16310b111",
  "isBasedOn": {
    "@id": "https://zml.ai/posts/laguna-s-2-1/"
  },
  "mainEntity": {
    "@id": "https://zml.ai/posts/laguna-s-2-1/",
    "@type": "CreativeWork",
    "archivedAt": {
      "@id": "https://aggr.aymericbeaumet.com/items/zml-ai/2026-07-21-laguna-s-2-1/#webpage"
    },
    "dateModified": "2026-07-21T18:00:00+00:00",
    "datePublished": "2026-07-21T18:00:00+00:00",
    "headline": "Laguna S 2.1",
    "timeRequired": "PT2M",
    "url": "https://zml.ai/posts/laguna-s-2-1/",
    "wordCount": 280
  },
  "name": "Archived snapshot: Laguna S 2.1",
  "preview": null,
  "reading_minutes": 2,
  "replicated_at": null,
  "source": "zml-ai",
  "source_name": "ZML - Model to Metal",
  "summary": "In close collaboration with Poolside, we’re happy to announce the support of Laguna S 2.1, their new open-weight model for agentic coding and long-horizon work. It is a 118B total parameters Mixture-of-Experts model with 8B activated parameters per token and supports a context window of up to 1M tokens, available in thinking and no-thinking modes. And it’s available today in ZML/LLMD with DFlash support. Most importantly (and as always with us), it’s available on all the supported platforms: NVIDIA, AMD, Intel, Google TPU and Apple Metal.",
  "tags": [],
  "temporalCoverage": "2026-09-08T10:17:10.166315+00:00",
  "title": "Laguna S 2.1",
  "url": "https://aggr.aymericbeaumet.com/items/zml-ai/2026-07-21-laguna-s-2-1/",
  "word_count": 280
}