{"id":1526,"date":"2026-06-24T20:49:02","date_gmt":"2026-06-24T19:49:02","guid":{"rendered":"https:\/\/entertainmentnews.site\/index.php\/2026\/06\/24\/using-visual-studio-codes-air-gapped-ai-model-mode\/"},"modified":"2026-06-24T20:49:12","modified_gmt":"2026-06-24T19:49:12","slug":"using-visual-studio-codes-air-gapped-ai-model-mode","status":"publish","type":"post","link":"https:\/\/entertainmentnews.site\/index.php\/2026\/06\/24\/using-visual-studio-codes-air-gapped-ai-model-mode\/","title":{"rendered":"Using Visual Studio Code\u2019s \u2018air-gapped\u2019 AI model mode"},"content":{"rendered":"
\n

The topic Using Visual Studio Code\u2019s \u2018air-gapped\u2019 AI model mode<\/strong> is currently the subject of lively discussion \u2014 readers and analysts are keeping a close eye on developments.<\/p>\n

This is taking place in a dynamic environment: companies\u2019 decisions and competitors\u2019 reactions can quickly change the picture.<\/p>\n

Microsoft has been pushing hard to make Visual Studio Code a major way to consume its AI services, mostly in the form of GitHub Copilot. GitHub Copilot\u2019s deep integration with VS Code brings many conveniences \u2014 inline autocomplete, for instance \u2014 but it\u2019s frustrating for those, like me, who would rather use another model provider, or even a locally hosted LLM, for those functions.<\/p>\n

Visual Studio Code 1.122 introduced a new feature, \u201cUse BYOK [Bring Your Own Key] without a GitHub sign-in,\u201d that allows you to \u201cuse chat, tools, and MCP servers in air-gapped or restricted environments where GitHub sign-in isn\u2019t possible.\u201d More importantly, it \u201cenables fully offline workflows with local models like Ollama.\u201d<\/p>\n

In other words, you can now use locally hosted LLMs for chat, tools, and Model Context Protocol servers inside Visual Studio Code. The one thing you still can\u2019t do is use a local LLM for inline and next-edit suggestions \u2014 at least, not without additional tooling.<\/p>\n

If you want to use a local LLM with VS Code\u2019s bring-your-own-model system, the first thing you need is a way to host the model. VS Code lacks a model-hosting mechanism of its own, although it\u2019s conceivable that a VS Code extension may offer something like that in future. That said, hosting models is complicated enough that a dedicated app is really needed for the job.<\/p>\n

One easy way to host models is via a product like LM Studio, a convenient GUI for standing up, serving, and managing LLMs on one\u2019s own hardware. The model host does not have to be the same system you run VS Code on, either. It can be on a server box you control, or on a cloud instance.<\/p>\n

\"\"<\/figure>\n

The choice of model is also important. Many models are powerful but won\u2019t run well on commodity hardware because they\u2019re simply too big. A good rule of thumb is to choose a model that fits into existing VRAM, along with the memory needed for a sizable token context (the more, the better). Also, the model should be suited to coding and development work. Some models in this vein that fit comfortably into 8GB VRAM include:<\/p>\n

Once you have a model up and running, you can integrate it with Visual Studio Code. If you\u2019ve disabled VS Code\u2019s AI features, you will need to turn them on. Make sure the setting chat.disableAIFeatures is turned off. You can find it in Settings | Chat | Miscellaneous.<\/p>\n

Third-party language models are managed through Visual Studio Code\u2019s language model list. Press Ctrl-Shift-P and type Manage Language Models to open the list of existing language models.<\/p>\n

Managing VS Code\u2019s AI language model list. The models available by default are only models available as external APIs, not models that run locally.<\/p>\n

First you will see a list of the built-in models, which are all externally hosted. To add a new model, select Add Models at the top right and select Custom Endpoint.<\/p>\n

Once you finish providing those answers, you\u2019ll be dropped into a modal editor for a JSON file that holds the details about the endpoint you\u2019re configuring.<\/p>\n

A newly created custom endpoint for a locally hosted model. The ID, name, and URL still need to be defined for this model to be useful.<\/p>\n

\"\"<\/figure>\n

You\u2019ll need to provide a few more details by typing them into the labeled fields:<\/p>\n

The other fields generally don\u2019t need editing. Most models have tool calling functionality. If you know for a fact that the model you\u2019re using doesn\u2019t have vision support, then set vision to false.<\/p>\n

Once you have these fields filled in, you can close the modal editor to save the changes. If you reload the Manage Language Models page, you\u2019ll now see your new endpoint:<\/p>\n

A newly created local endpoint. The choice of name and group is arbitrary. \u201cCustom Endpoint\u201d is the default name for a newly created group of endpoints.<\/p>\n

You should now be able to launch the chat window and use the defined model for conversation and utilities:<\/p>\n

Conversing with the local model using VS Code\u2019s chat window. Note the selected code block in the left pane that is being used as the context for the conversation.<\/p>\n

One current, and major, limitation of Visual Studio Code\u2019s BYOK functionality is that it only works for chat and utility tasks. It doesn\u2019t allow you to use a local model for inline suggestions or code completions. The only way to take advantage of local models for expanded functionality with VS Code is to use a third-party tool like Continue.<\/p>\n

It isn\u2019t clear if Microsoft will eventually lift this restriction. GitHub Copilot integration in VS Code is a large part of how Copilot as a service reaches its target audience. For the time being, you can certainly use third-party and local models for a significant part of your AI-assisted development work in VS Code, and you can close the functionality gap with additional tooling.<\/p>\n