> ## Documentation Index
> Fetch the complete documentation index at: https://docs-apexspriteai.reliatrack.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Get ApexSpriteAI running: install, configure, and test

> A step-by-step quickstart that gets you from zero to a running AI coding assistant using LM Studio and the Claude Code CLI on your Mac.

ApexSpriteAI pairs the Claude Code CLI with a locally hosted LLM to give you a fast, private AI coding assistant that supports the full Model Context Protocol (MCP) tool system. This guide walks you through every step — from installing LM Studio to sending your first query — and takes about 15 minutes to complete.

<Steps>
  <Step title="Install LM Studio">
    Download and install [LM Studio](https://lmstudio.ai) on the machine that has your GPU. LM Studio provides a graphical interface for downloading models and running a local OpenAI-compatible API server.

    Once installed, open LM Studio and sign in (or skip sign-in). You should land on the **Discover** tab where you can search for models.

    <Note>
      LM Studio 0.4.1 or later is required. Earlier versions may not support the `/v1/messages` endpoint that Claude Code uses.
    </Note>
  </Step>

  <Step title="Download the Qwen2.5-Coder-32B model">
    In LM Studio's **Discover** tab, search for `Qwen2.5-Coder-32B-Instruct` and download a quantized GGUF variant (Q4\_K\_M is a good balance of speed and quality).

    This model is the recommended choice for ApexSpriteAI because it:

    * Runs at low latency on 32 GB or more of GPU or unified RAM
    * Matches Claude 3.5 Sonnet on many coding benchmarks
    * Reliably follows the tool-calling format that MCP depends on

    <Tip>
      If you have 128 GB of unified RAM, you can also try `Llama-3.3-70B-Instruct` for stronger general reasoning. For the fastest possible responses on any hardware, `DeepSeek-Coder-V2-Lite-Instruct` (16B) is a blazing-fast alternative.
    </Tip>
  </Step>

  <Step title="Start the local server on port 1234">
    In LM Studio, switch to the **Developer** tab (the `</>` icon in the left sidebar). Load your downloaded model using the model selector at the top, then click **Start Server**.

    LM Studio will bind to `0.0.0.0:1234` by default, making the server reachable from other machines on your network (including over Tailscale). Confirm the server is running by checking for the green status indicator and a log entry like:

    ```
    Server listening on http://0.0.0.0:1234
    ```

    You can verify the server is reachable from your Mac with a quick connectivity check:

    ```bash theme={null}
    nc -vz 100.x.x.x 1234
    ```

    Replace `100.x.x.x` with your server's Tailscale IP. You should see `Connection to ... succeeded`.
  </Step>

  <Step title="Install Claude Code CLI">
    On your Mac (or local workstation), install the Claude Code CLI globally using npm:

    ```bash theme={null}
    npm install -g @anthropic-ai/claude-code
    ```

    Confirm the installation succeeded:

    ```bash theme={null}
    claude --version
    ```

    <Note>
      Node.js 18 or later is required. Run `node --version` to check. If you need to upgrade, use [nvm](https://github.com/nvm-sh/nvm) or download the latest LTS release from [nodejs.org](https://nodejs.org).
    </Note>
  </Step>

  <Step title="Configure Claude Code to use your local LM Studio server">
    Create (or edit) the Claude Code configuration file at `~/.claude/config.json`. This tells Claude Code to send requests to your LM Studio server instead of Anthropic's cloud API.

    ```json ~/.claude/config.json theme={null}
    {
      "ANTHROPIC_BASE_URL": "http://100.x.x.x:1234",
      "ANTHROPIC_API_KEY": "lm-studio"
    }
    ```

    Replace `100.x.x.x` with the actual Tailscale IP of your LM Studio server. The `ANTHROPIC_API_KEY` value is arbitrary — LM Studio does not validate it — but the field must be present.

    <Note>
      If you are running LM Studio on the same machine as Claude Code, use `http://localhost:1234` as the base URL instead.
    </Note>

    <Tip>
      You can also set these values as environment variables if you prefer not to store them in a config file: `export ANTHROPIC_BASE_URL=http://100.x.x.x:1234` and `export ANTHROPIC_API_KEY=lm-studio`.
    </Tip>
  </Step>

  <Step title="Run your first query">
    Open a terminal in any project directory and run:

    ```bash theme={null}
    claude "Explain what this project does and suggest one improvement"
    ```

    Claude Code reads your local files, formats the request with available MCP tools, and sends it to LM Studio. You should see a response stream back within a few seconds.

    For an interactive session where you can ask follow-up questions, run `claude` with no arguments:

    ```bash theme={null}
    claude
    ```

    <Check>
      If you see a response, your setup is complete. Claude Code is now running fully locally with MCP tool support.
    </Check>
  </Step>
</Steps>

## Troubleshooting

<AccordionGroup>
  <Accordion title="Claude Code returns an authentication error">
    Check that `ANTHROPIC_API_KEY` is present in `~/.claude/config.json`. The value can be anything — LM Studio ignores it — but omitting the key causes Claude Code to reject the configuration.
  </Accordion>

  <Accordion title="Connection refused or timeout on port 1234">
    Confirm LM Studio's server is running (green indicator in the Developer tab). If you are connecting over Tailscale, verify both machines appear as connected peers with `tailscale status` and that you are using the correct `100.x.x.x` IP.
  </Accordion>

  <Accordion title="Responses are very slow">
    Switch to a smaller model. The 32B Qwen model is the recommended starting point. If you loaded a 70B or 120B model, latency will be significantly higher. See the [model selection guide](/guides/model-selection) for a detailed comparison.
  </Accordion>

  <Accordion title="MCP tools are not executing">
    MCP tools run locally on your Mac through the Claude Code CLI, regardless of where the LLM is hosted. Run `claude mcp list` to see which tools are registered. If the list is empty, add tools with `claude mcp add <name> <command>`.
  </Accordion>
</AccordionGroup>