{"slug": "laguna-xs-model-in-opencode", "title": "Laguna XS Model in OpenCode", "summary": "Poolside AI's Laguna XS model, a small local LLM, performed well in refactoring Rust code via OpenCode, making relatively few errors and handling tool calls correctly except for escaped quotes. The 20.3 GB 4-bit quantized GGUF model outperformed Qwen 3.6 35B, Gemma 4, and North Mini Code in targeted code changes, though it struggled with open-ended optimization tasks.", "body_md": "I am continually interested in having a small, **local LLM** (running in `llama-cpp`\n\n) that can edit and add simple features to programs written in Rust and similar languages. Recently support for the **Laguna** models from Poolside AI (an American AI company) was added to `llama-cpp`\n\n. I tried out the smaller version (**Laguna XS**) locally.\n\nI used **OpenCode** and had the model perform a series of **refactoring changes** on the code base. It made **relatively few errors** and almost all of the tool calls worked correctly (it became confused with escaped quotes once, and I don't blame it).\n\nI used the **official GGUF** 4-bit quantized model from Poolside on their Hugging Face page, `Laguna-XS-2.1-Q4_K_M.gguf`\n\n. It weighed in at 20.3 GB (good thing I have fairly fast Internet these days).\n\nOverall, I found **Laguna XS** to **perform well**, probably better than Qwen 3.6 35B, Gemma 4 and North Mini Code. I started feeling more confident in it, and made a series of refactoring changes which mostly worked correctly. It struggled on an open-ended task (\"optimize this function\") but for more targeted changes, I feel Laguna XS is likely better than the other open-weights models supported by my 12 GB Nvidia GPU.", "url": "https://wpnews.pro/news/laguna-xs-model-in-opencode", "canonical_source": "https://www.dotnetperls.com/2026_7_22_laguna-xs-model-opencode", "published_at": "2026-07-22 07:00:00+00:00", "updated_at": "2026-07-22 14:54:34.648134+00:00", "lang": "en", "topics": ["large-language-models", "ai-tools", "developer-tools"], "entities": ["Poolside AI", "Laguna XS", "OpenCode", "llama-cpp", "Hugging Face", "Qwen 3.6 35B", "Gemma 4", "North Mini Code"], "alternates": {"html": "https://wpnews.pro/news/laguna-xs-model-in-opencode", "markdown": "https://wpnews.pro/news/laguna-xs-model-in-opencode.md", "text": "https://wpnews.pro/news/laguna-xs-model-in-opencode.txt", "jsonld": "https://wpnews.pro/news/laguna-xs-model-in-opencode.jsonld"}}