--- title: GitHub Copilot Fusion now supports selection of local models description: GitHub Copilot Fusion now supports routing between local and cloud models in experimental preview. It works in Copilot CLI, the Copilot app, and VS Code. On... canonical: https://daily.dev/posts/github-copilot-fusion-now-supports-selection-of-local-models-i1gt1vvef twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: GitHub Copilot Fusion now supports selection of local models | daily.dev og:description: GitHub Copilot Fusion now supports routing between local and cloud models in experimental preview. It works in Copilot CLI, the Copilot app, and VS Code. On... og:url: https://daily.dev/posts/github-copilot-fusion-now-supports-selection-of-local-models-i1gt1vvef og:image: https://api.daily.dev/og/posts/i1gT1VvEF.png og:image:alt: GitHub Copilot Fusion now supports selection of local models 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. # GitHub Copilot Fusion now supports selection of local models **[GitHub Changelog](https://daily.dev/sources/github_updates)** · 3 min read · 1 upvotes · 0 comments ## Summary GitHub Copilot Fusion now supports routing between local and cloud models in experimental preview. It works in Copilot CLI, the Copilot app, and VS Code. On Windows, you can download and configure MAI Code 1.1 Flash through the Windows ML provider with a managed setup. On Windows, macOS, and Linux, you can manually configure MAI Code 1.1 Flash or Qwen3.8 Flash Next through a local OpenAI-compatible server. Selecting 'Standard' in Copilot Fusion lets Copilot choose between eligible local and cloud models. Local inference doesn't make sessions offline, since routing decisions still happen in the cloud, and local models may have different safety protections than cloud models. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I enable local model routing in GitHub Copilot CLI? Enable experimental mode in Copilot CLI and open the /model command to follow the setup prompts. On supported Windows devices, you can download and configure MAI Code 1.1 Flash through the Windows ML provider. On Windows, macOS, and Linux, you can also manually configure a local OpenAI-compatible server running MAI Code 1.1 Flash or Qwen3.8 Flash Next. _daily.dev surfaces setup changes like this for developers rolling out Copilot CLI updates._ ### Does using a local model with GitHub Copilot make my session work offline? No, local inference does not make a Copilot session offline. Copilot Fusion still makes routing decisions in the cloud even when using an on-device model, and local models may have different safety protections than Copilot-provided cloud models. _Developers weighing local versus cloud AI models can track these trade-offs on daily.dev._ ### What local models does GitHub Copilot Fusion support? GitHub Copilot Fusion supports MAI Code 1.1 Flash, which can be managed and downloaded through the Windows ML provider on supported Windows devices, and both MAI Code 1.1 Flash and Qwen3.8 Flash Next can be configured manually through a local OpenAI-compatible server on Windows, macOS, and Linux. _Teams choosing which local models to pair with Copilot can follow updates like this on daily.dev._ ## Similar posts on daily.dev - [Auto model selection is generally available in GitHub Copilot in Visual Studio Code](https://daily.dev/posts/auto-model-selection-is-generally-available-in-github-copilot-in-visual-studio-code-cvhnbwf95) · GitHub Changelog · 0 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 - [MAI-Code-1.1-Flash available in GitHub Copilot](https://daily.dev/posts/mai-code-1-1-flash-available-in-github-copilot-b3ij55irv) · GitHub Changelog · 0 upvotes · 0 comments --- Tags: [#github](https://daily.dev/tags/github), [#vscode](https://daily.dev/tags/vscode), [#local-ai](https://daily.dev/tags/local-ai) [View this post on daily.dev](https://daily.dev/posts/github-copilot-fusion-now-supports-selection-of-local-models-i1gt1vvef) ```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":"TechArticle","headline":"GitHub Copilot Fusion now supports selection of local models","url":"https://daily.dev/posts/github-copilot-fusion-now-supports-selection-of-local-models-i1gt1vvef","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/github-copilot-fusion-now-supports-selection-of-local-models-i1gt1vvef"},"datePublished":"2026-10-28T16:16:53.837Z","dateModified":"2026-10-28T16:24:51.899Z","description":"GitHub Copilot Fusion now supports routing between local and cloud models in experimental preview. It works in Copilot CLI, the Copilot app, and VS Code. On...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/fe754097cdade191b4978850703ab057?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/fe754097cdade191b4978850703ab057?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"GitHub Changelog","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"GitHub Changelog","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/15004b7835da4d89b02b115871f0f6dc","url":"https://daily.dev/sources/github_updates"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/github-copilot-fusion-now-supports-selection-of-local-models-i1gt1vvef","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"github,vscode,local-ai","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"GitHub Changelog","item":"https://daily.dev/sources/github_updates"},{"@type":"ListItem","position":3,"name":"GitHub Copilot Fusion now supports selection of local models"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/github-copilot-fusion-now-supports-selection-of-local-models-i1gt1vvef#faq","mainEntity":[{"@type":"Question","name":"How do I enable local model routing in GitHub Copilot CLI?","acceptedAnswer":{"@type":"Answer","text":"Enable experimental mode in Copilot CLI and open the /model command to follow the setup prompts. On supported Windows devices, you can download and configure MAI Code 1.1 Flash through the Windows ML provider. On Windows, macOS, and Linux, you can also manually configure a local OpenAI-compatible server running MAI Code 1.1 Flash or Qwen3.8 Flash Next. daily.dev surfaces setup changes like this for developers rolling out Copilot CLI updates."}},{"@type":"Question","name":"Does using a local model with GitHub Copilot make my session work offline?","acceptedAnswer":{"@type":"Answer","text":"No, local inference does not make a Copilot session offline. Copilot Fusion still makes routing decisions in the cloud even when using an on-device model, and local models may have different safety protections than Copilot-provided cloud models. Developers weighing local versus cloud AI models can track these trade-offs on daily.dev."}},{"@type":"Question","name":"What local models does GitHub Copilot Fusion support?","acceptedAnswer":{"@type":"Answer","text":"GitHub Copilot Fusion supports MAI Code 1.1 Flash, which can be managed and downloaded through the Windows ML provider on supported Windows devices, and both MAI Code 1.1 Flash and Qwen3.8 Flash Next can be configured manually through a local OpenAI-compatible server on Windows, macOS, and Linux. Teams choosing which local models to pair with Copilot can follow updates like this on daily.dev."}}]} ```