--- title: Usages of local LLM | daily.dev description: A developer shares their local LLM setup inside VS Code using two lightweight models: Qwen 3.5 9B for chat and agentic workflows, and Granite 4 3B for fast... canonical: https://daily.dev/posts/usages-of-local-llm-u72fyixx3 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Usages of local LLM | daily.dev og:description: A developer shares their local LLM setup inside VS Code using two lightweight models: Qwen 3.5 9B for chat and agentic workflows, and Granite 4 3B for fast... og:url: https://daily.dev/posts/usages-of-local-llm-u72fyixx3 og:image: https://api.daily.dev/og/posts/U72fYIxX3.png og:image:alt: Usages of local LLM 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. # Usages of local LLM **[MD Abdur Rahman Nur Jamil](https://daily.dev/sources/j478satqhv7i2qjbfcmqh)** · [@mabdurrahman](https://daily.dev/mabdurrahman) · 1 min read · 4 upvotes · 3 comments ## Summary A developer shares their local LLM setup inside VS Code using two lightweight models: Qwen 3.5 9B for chat and agentic workflows, and Granite 4 3B for fast inline autocomplete. The entire setup runs offline on personal hardware, offering zero latency and full privacy. The author recommends it for anyone with a capable GPU. ## Content I set up a local setup inside VS Code using two lean models, and the workflow is remarkably smooth: Qwen 3.5 9B handles the main chat and agentic workflows. Granite 4 3B takes care of fast, inline autocomplete suggestions. Everything runs on my own hardware, completely offline, with zero latency and full privacy. The agentic era of coding feels entirely different when you have local models assisting you every step of the way. If you have a decent GPU lying around, it is well worth setting up. ## Community discussion Top comments from developers on daily.dev. **@deepeshhaldankar97** · 2 upvotes > @mabdurrahman can u tell me more about your setup how u did it ..? > what is Ur hardware specs and all.. ## Similar posts on daily.dev - [Set Up Local LLM Code Completion in VS Code with Ollama](https://daily.dev/posts/set-up-local-llm-code-completion-in-vs-code-with-ollama-qotyztssi) · SitePoint · 1 upvotes · 0 comments - [I ditched VS Code's Copilot for a local LLM, and I'm getting more done offline](https://daily.dev/posts/i-ditched-vs-code-s-copilot-for-a-local-llm-and-i-m-getting-more-done-offline-zbcs3qkqt) · XDA Developers · 0 upvotes · 0 comments --- Tags: [#vscode](https://daily.dev/tags/vscode), [#local-ai](https://daily.dev/tags/local-ai), [#qwen](https://daily.dev/tags/qwen) [View this post on daily.dev](https://daily.dev/posts/usages-of-local-llm-u72fyixx3) ```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/usages-of-local-llm-u72fyixx3","headline":"Usages of local LLM","text":"A developer shares their local LLM setup inside VS Code using two lightweight models: Qwen 3.5 9B for chat and agentic workflows, and Granite 4 3B for fast inline autocomplete. The entire setup runs offline on personal hardware, offering zero latency and full privacy. The author recommends it for anyone with a capable GPU.","url":"https://daily.dev/posts/usages-of-local-llm-u72fyixx3","datePublished":"2026-08-11T18:48:34.212Z","dateModified":"2026-09-13T21:28:32.959Z","author":{"@type":"Person","name":"MD Abdur Rahman Nur Jamil","url":"https://daily.dev/mabdurrahman","image":"https://media.daily.dev/image/upload/s--Y4BlqifR--/f_auto/v1748712069/avatars/avatar_j478sATQhv7i2qjbFcMqH?_a=BAMClqUq0","description":"I am developing digital symphonies with MERN magic. Newbie coder, boundlessly curious","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":560}},"image":"https://media.daily.dev/image/upload/s--yzd-qVvK--/f_auto/v1786474115/posts/U72fYIxX3?_a=BAMAMicg0","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":4},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":3}],"comment":[{"@type":"Comment","text":"@mabdurrahman can u tell me more about your setup how u did it …?\nwhat is Ur hardware specs and all…","datePublished":"2026-08-18T07:07:11.633Z","url":"https://daily.dev/posts/U72fYIxX3#c-hHfJayfCq","author":{"@type":"Person","name":"Deepesh Haldankar","url":"https://daily.dev/deepeshhaldankar97","image":"https://media.daily.dev/image/upload/s--cx_32bE1--/f_auto/v1784271060/avatars/avatar_m1ddWiyurlfSDkRS0l5ZW?_a=BAMAMicg0"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2}}],"isPartOf":{"@type":"WebPage","url":"https://daily.dev/sources/j478satqhv7i2qjbfcmqh","name":"MD Abdur Rahman Nur Jamil"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"MD Abdur Rahman Nur Jamil","item":"https://daily.dev/sources/j478satqhv7i2qjbfcmqh"},{"@type":"ListItem","position":3,"name":"Usages of local LLM"}]} ```