--- title: Local AI: LM Studio + VS Code setup guide | daily.dev description: A setup guide for running local AI models using LM Studio on a MacBook and integrating them with Visual Studio Code via the Continue plugin. The author tested... canonical: https://daily.dev/posts/local-ai-lm-studio-vs-code-setup-guide-igwpbruvo twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Local AI: LM Studio + VS Code setup guide | daily.dev og:description: A setup guide for running local AI models using LM Studio on a MacBook and integrating them with Visual Studio Code via the Continue plugin. The author tested... og:url: https://daily.dev/posts/local-ai-lm-studio-vs-code-setup-guide-igwpbruvo og:image: https://api.daily.dev/og/posts/IgwpBrUVO.png og:image:alt: Local AI: LM Studio + VS Code setup guide og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Local AI: LM Studio + VS Code setup guide **[Think As A Dev](https://daily.dev/sources/thinkasadev)** · [@giogdev](https://daily.dev/giogdev) · 2 min read · 0 upvotes · 0 comments ## Summary A setup guide for running local AI models using LM Studio on a MacBook and integrating them with Visual Studio Code via the Continue plugin. The author tested 30B parameter models and found them surprisingly capable. The post also touches on the broader context of commercial AI tools like Claude Code and GitHub Copilot facing access restrictions, making local alternatives more appealing. A follow-up article is promised covering a real-world use case involving legacy code extraction and Angular component generation. ## Content The AI world is constantly shifting, with Anthropic looking to pull Claude Code from Pro plans and GitHub Copilot closing subscriptions to new users. Where is all this heading? I bought my first MacBook a few months ago, and the first thing I wanted to figure out was how well it could run local models, how they stack up against the big commercial ones, and how to get the most out of them. In the post below I walk you through how I set up LM Studio to run a model locally and hook it up to Visual Studio Code using the Continue plugin. I tested models with 30B parameters, which are nowhere near the level of something like Opus or Sonnet, but honestly the potential surprised me. These days I'm working on a pretty interesting project: extracting business logic from a legacy application using a Claude Code skill, then reshaping and documenting it across several markdown files. That output is then picked up by another skill (on an Angular project) that handles creating the base components, services and stores, applying the logic extracted and documented in the first artifacts. The Angular project skill relies on a set of templates and guardrails, and using less capable AI models could actually make a real difference here, helping us save a lot of tokens. I'll explain well this project in a follow-up article, stay tuned! In the meantime, if you want to run a local model with LM Studio, check out my article! 🔗 [https://www.thinkasadev.com/en/local-ai-with-vs-code-and-continue-2/](https://www.thinkasadev.com/en/local-ai-with-vs-code-and-continue-2/) ## Similar posts on daily.dev - [Local AI Coding Assistant: Complete VS Code \+ Ollama \+ Continue Setup](https://daily.dev/posts/local-ai-coding-assistant-complete-vs-code-ollama-continue-setup-5hoo7jcgh) · SitePoint · 0 upvotes · 1 comments - [I replaced GitHub Copilot with a self-hosted AI and I won’t go back](https://daily.dev/posts/i-replaced-github-copilot-with-a-self-hosted-ai-and-i-won-t-go-back-wbbte4aen) · XDA Developers · 1 upvotes · 0 comments --- Tags: [#ai-assisted-development](https://daily.dev/tags/ai-assisted-development), [#lm-studio](https://daily.dev/tags/lm-studio), [#local-ai](https://daily.dev/tags/local-ai), [#vscode](https://daily.dev/tags/vscode) [View this post on daily.dev](https://daily.dev/posts/local-ai-lm-studio-vs-code-setup-guide-igwpbruvo) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"DiscussionForumPosting","mainEntityOfPage":"https://daily.dev/posts/local-ai-lm-studio-vs-code-setup-guide-igwpbruvo","headline":"Local AI: LM Studio + VS Code setup guide","text":"A setup guide for running local AI models using LM Studio on a MacBook and integrating them with Visual Studio Code via the Continue plugin. The author tested 30B parameter models and found them surprisingly capable. The post also touches on the broader context of commercial AI tools like Claude Code and GitHub Copilot facing access restrictions, making local alternatives more appealing. A follow-up article is promised covering a real-world use case involving legacy code extraction and Angular component generation.","url":"https://daily.dev/posts/local-ai-lm-studio-vs-code-setup-guide-igwpbruvo","datePublished":"2026-04-23T08:05:37.800Z","dateModified":"2026-06-18T02:16:23.894Z","author":{"@type":"Person","name":"Giorgio","url":"https://daily.dev/giogdev","image":"https://media.daily.dev/image/upload/s--VzsFQRBX--/f_auto/v1742975876/avatars/avatar_bUTlUNyzqZVBNMJnTQ8PW","description":"Hi, I'm Giorgio!\nI work as software developer and I love everything is nerd! ","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":210}},"image":"https://media.daily.dev/image/upload/s--XjI98urn--/f_auto/v1776931538/posts/IgwpBrUVO?_a=BAMAMiWQ0","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"isPartOf":{"@type":"WebPage","url":"https://daily.dev/squads/thinkasadev","name":"Think As A Dev"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Think As A Dev","item":"https://daily.dev/squads/thinkasadev"},{"@type":"ListItem","position":3,"name":"Local AI: LM Studio + VS Code setup guide"}]} ```