Ollama & Open-webui Installation Guide

Installing Ollama

Windows Installation

Note: Ollama now has native Windows support! Simply download and run the Windows installer.

Download and install Ollama directly from the official website:

Download Ollama for Windows

After installation:
  1. Double-click the installer (OllamaSetup.exe)
  2. Follow the installation wizard
  3. Open your favorite terminal (Command Prompt or PowerShell)
  4. Run ollama run llama2 to start using Ollama
Run Ollama from the Start menu or desktop shortcut
  • The Ollama service will start automatically
  • You can use Ollama from Command Prompt or PowerShell

    • Installing Open-webui

    Windows Requirements

    Step 1: Install Visual Studio Build Tools

    Download and install Visual Studio Build Tools 2022:

    Download Visual Studio Build Tools 2022

    During installation, follow these steps:
    1. In the Visual Studio Installer, first select "Desktop development with C++" workload
    2. Then click on the "Individual components" tab at the top
    3. In the search box, type "MSVC" to filter components
    4. Select "MSVC v143 - VS 2022 C++ x64/x86 build tools" for the latest C++ build tools
    5. Clear the search box and type "SDK" to filter components
    6. Select either "Windows 10 SDK" or "Windows 11 SDK" based on your Windows version
    7. Click "Install" to begin installation

    Note: The installer may show many components, but you only need the ones listed above for Open-webui.

    Step 2: Install Python 3.10 or higher

    Download and install Python from the official website:

    Download Python

    Step 3: Install Open-webui

    pip install open-webui

    Step 4: Run Open-webui

    open-webui serve
    After starting Open-webui, access the interface at: http://localhost:8080

    Ollama Model Management and Usage

    Windows Command Line Instructions

    Important: Make sure Ollama service is running before executing these commands. You can start it from the Windows Start Menu or by running Ollama application.

    Basic Ollama Commands

    ollama list

    Lists all installed models

    ollama pull llama2

    Downloads and installs the Llama 2 model (you can replace 'llama2' with other model names)

    ollama run llama2

    Starts an interactive chat session with the Llama 2 model

    Step 3: Install Open-webui

    pip install open-webui

    Step 4: Run Open-webui

    python -m openwebui

    Available Models

    Here's a comprehensive list of available models:

    View Latest Models on Ollama.com →
    Model Name Size Run Command
    Moondream 2 829MB ollama run moondream
    Llama 3.2 (1B) 1.3GB ollama run llama3.2:1b
    Gemma 2 (2B) 1.6GB ollama run gemma2:2b
    Llama 3.2 2.0GB ollama run llama3.2
    Phi 4 Mini 2.5GB ollama run phi4-mini
    Code Llama 3.8GB ollama run codellama
    Llama 2 Uncensored 3.8GB ollama run llama2-uncensored
    Mistral 4.1GB ollama run mistral
    Neural Chat 4.1GB ollama run neural-chat
    LLaVA 4.5GB ollama run llava
    DeepSeek-R1 4.7GB ollama run deepseek-r1
    Llama 3.1 4.7GB ollama run llama3.1
    Granite-3.2 4.9GB ollama run granite3.2
    Gemma 2 (27B) 16GB ollama run gemma2:27b
    QwQ 20GB ollama run qwq
    Llama 3.3 43GB ollama run llama3.3
    Llama 3.2 Vision (90B) 55GB ollama run llama3.2-vision:90b
    Llama 3.1 (405B) 231GB ollama run llama3.1:405b
    DeepSeek-R1 (671B) 404GB ollama run deepseek-r1:671b

    Advanced Commands

    ollama rm llama2

    Removes a model from your system

    ollama serve

    Starts the Ollama API server (usually not needed as it runs automatically)

    Ollama Command Line Reference

    Basic Usage

    ollama [flags]
ollama [command]

    Server Management Commands

    ollama serve       # Start the Ollama server
ollama ps          # List running models
ollama stop        # Stop a running model

    Use these commands to manage the Ollama server and running model instances.

    Model Management Commands

    ollama list        # List all installed models
ollama pull        # Pull a model from a registry
ollama push        # Push a model to a registry
ollama rm          # Remove a model
ollama cp          # Copy a model
ollama show        # Show information for a model

    These commands help you manage your local model collection.

    Model Creation and Execution

    ollama create      # Create a model from a Modelfile
ollama run         # Run a model

    Use these commands to create custom models and run interactive sessions.

    Help and Version

    ollama --help      # Show help information
ollama -v          # Show version information
ollama [command] --help  # Get help for specific commands

    Access help documentation and version information with these commands.

    Setting up Open-webui with Ollama

    Configuration Steps

    Before starting Open-webui, ensure that: