Installation & Setup Guide

This guide describes how to install Local LLM Server Manager on Windows and Linux systems.

Testing & Setup Matrix

Local LLM Server Manager uses a modular architecture. You only need to install components for the features you intend to test.

Feature Area	Role in Stack	Prerequisite Requirement	What It Enables
Core Manager & Dashboard	REQUIRED	Windows 10/11 x64 or Linux x64	Hardware telemetry, VRAM bar, system tray, reverse proxy, web dashboard.
Ollama Engine	Optional	Ollama installed	Local LLM text generation, GGUF downloads, KV cache calculator.
Stable Diffusion Forge	Optional	SD Forge installed	Local image generation, CivitAI checkpoint and LoRA downloads.
ComfyUI Engine	Optional	ComfyUI installed	3D mesh reconstruction, video generation, and FLUX workflows.
Kokoro TTS Engine	Optional	Python environment or Audio Pack	Local speech synthesis with OpenAI-compatible audio API.
AI Chat Assistant	Optional	LiteLLM gateway or OpenAI endpoint	In-app assistant, multimodal screenshot analysis, and app control.
*Feature Packs (`ext_`)**	Optional	Installed via Settings tab	Video ComfyUI presets (`ext_video`) and Audio workflows (`ext_audio`).

IMPORTANT

The release package is self-contained. You do not need to install the .NET SDK or .NET runtime to run the application.

Windows Installation

Choose one of two installation methods for Windows.

Method 1: Official Windows Installer (Recommended)

The official installer configures the application, sets up desktop shortcuts, and registers the background Windows Service.

Open the GitHub Releases page in your web browser.
Download the latest installer executable (LocalLLMServerManager-Setup.exe).
Right-click the downloaded file and select Run as administrator.
Select your desired installation components in the setup wizard:
- Install Windows Service: Starts the server in headless mode when the machine boots.
- Auto-Start System Tray App: Starts the system tray application when you sign in.
- Desktop and Start Menu Shortcuts: Creates application icons for quick access.
Click Install to complete the installation process.

NOTE

The installer performs seamless in-place upgrades. The installer terminates older background processes safely, preserves your settings.json file, and restarts the background service.

IMPORTANT

Administrator privileges are required to register and start the Windows Service.

Method 2: Standalone Portable Archive (.zip)

Use the portable archive to test the application without modifying system services.

Download the LocalLLMServerManager-win-x64.zip archive from the Releases page.
Extract the archive contents into a folder (for example: C:\LocalLLMServerManager).
Open the extracted folder in File Explorer.
Double-click LocalLLMServerManager.exe to start the application.
The desktop window and system tray icon appear immediately.

Linux Installation

Choose the automated script for system integration, or run the application in headless service mode.

Method 1: Automated Linux Script (`install_linux.sh`)

The automated script configures system paths, registers a systemd unit, and installs desktop menu entries.

Open a terminal on your Linux machine.

Clone the repository or download the source archive:

bash

git clone https://github.com/spelech/LocalLLMServerManager.git
cd LocalLLMServerManager

Run the installer script with root privileges:
bash
```
sudo ./scripts/install_linux.sh
```

The script performs the following actions automatically:

Stops any active localllmmanager.service instance.
Preserves existing user settings in settings.json.
Installs binaries to /usr/local/share/LocalLLMServerManager.
Creates a binary symlink at /usr/local/bin/localllmmanager.
Registers and enables the localllmmanager.service systemd daemon.
Installs the desktop launcher file (localllmmanager.desktop).

Method 2: Running the Native GUI on Linux Desktop

Launch the native Avalonia user interface on Linux desktop sessions:

Open your terminal.
Type localllmmanager and press Enter:
bash
```
localllmmanager
```

The native dark Avalonia desktop window opens on both X11 and Wayland display environments.

Method 3: Running Headless CLI Mode

Run the server in headless mode on Linux servers without a graphical desktop:

Open your terminal.
Navigate to the installation directory.
Start the application with the service argument:
bash
```
dotnet run -- --service
```

Alternatively, control the background daemon with systemctl:

bash

# Start the background service
sudo systemctl start localllmmanager

# Inspect service status
sudo systemctl status localllmmanager

# Stop the background service
sudo systemctl stop localllmmanager

Remote Server & SSH Port Forwarding

Access the complete web dashboard on a headless remote server using SSH port forwarding:

Connect to your remote host with port 5246 forwarded to your local machine:
bash
```
ssh -L 5246:localhost:5246 user@your-remote-host
```
Start the headless service on the remote server:
bash
```
sudo systemctl start localllmmanager
```
Open http://localhost:5246 in your local web browser.

TIP

The web interface provides full access to VRAM telemetry, model downloads, and the 3D WebGL viewer through the forwarded SSH port.

Verify Installation

Verify that the local server operates correctly:

Open your web browser.
Navigate to http://localhost:5246/health.
Verify that the response returns HTTP status 200 OK with JSON health information.
Navigate to http://localhost:5246 to view the user interface.

Next Steps

Proceed to the First-Time Configuration Guide to configure engine paths and network ports.

Installation & Setup Guide ​

Testing & Setup Matrix ​

Windows Installation ​

Method 1: Official Windows Installer (Recommended) ​

Method 2: Standalone Portable Archive (.zip) ​

Linux Installation ​

Method 1: Automated Linux Script (install_linux.sh) ​

Method 2: Running the Native GUI on Linux Desktop ​

Method 3: Running Headless CLI Mode ​

Remote Server & SSH Port Forwarding ​

Verify Installation ​

Next Steps ​