> For the complete documentation index, see [llms.txt](https://docs.desktop.faros.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.desktop.faros.ai/power-ups/local-models.md). # Local Models Local models run supported inference on your Mac. They can provide capabilities such as local decisions, embeddings, or generation, depending on the model and runtime. ## Check Availability 1. Open **Power Ups** and inspect the Local Models Power Up. 2. See if you can enable the Power Up. 3. If you don't have Local Models installed, wait for verification and activation. 4. Check that the capability reports ready before using on it. Downloaded files alone do not establish that a model can run. Compatibility depends on the hardware, macOS version, runtime, model format, and task. ## System Models and Additional Models Apple's system model is managed by macOS. If Faros reports it unavailable, follow the displayed System Settings guidance. Additional models use their own supported installation and runtime paths. Available models and acquisition controls vary by release. Do not assume that every model family or downloaded model can perform every task. ## Manage Resources Downloads consume disk space, and loaded models use memory. Disabling a capability can retain downloaded assets; disabling and removing are different operations. If installation or activation fails, use the offered recovery action and inspect the reported reason. Organization policy can restrict downloads or inference. ## Where Models Are Used Each consuming Power Up determines whether it uses a compatible local model. Having local models available does not reroute all AI-tool requests to your Mac or replace those tools' provider accounts. ## Related Guides * [Solve Common Problems](/troubleshooting/solve-common-problems.md) * [Understand Your Data](/settings-and-privacy/understand-your-data.md) --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.desktop.faros.ai/power-ups/local-models.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.