OllaMan DocsQuick Start
Zero-code setup, get started with OllaMan in 5 minutes
Welcome to OllaMan
OllaMan is a professional Ollama model management desktop application that makes managing and using AI models easy through a friendly graphical interface, no coding required.
This guide will walk you through the complete process from installation to your first conversation.
Step 1: Install Ollama
OllaMan requires Ollama as the backend service. Let's install it first.
Download and Install
Visit ollama.com/download and install Ollama for your operating system.
Verify Installation
After installation, Ollama will automatically run in the background. Let's verify:
- Open your web browser
- Navigate to
http://localhost:11434 - If the page displays "Ollama is running", congratulations, installation successful!
Can't see this message?
If your browser shows "Cannot connect", please check:
- System tray (Windows) or menu bar (macOS) for the Ollama icon
- Try restarting the Ollama application
- Windows users can check Ollama service status in "Services"
Step 2: Configure Ollama
Before connecting OllaMan, we need to configure Ollama with necessary settings.
Enable Network Access
If the Ollama server is deployed on a remote host, you need to configure it to allow external network access:
Locate the Ollama Icon
- Windows: Find the Ollama icon in the system tray at the bottom-right corner
- macOS: Find the Ollama icon in the menu bar at the top-right corner
Open Settings Menu
Right-click (or left-click) the Ollama icon and select "Settings"
Enable Network Access
In the settings window, find and enable the "Expose Ollama to the network" option
Why enable network access?
Security Notice: This option allows other devices on the same network to access your Ollama service.
- Convenience: Enables OllaMan and other management tools to connect
- Security: Only enable in trusted network environments
- Recommendation: Default settings are secure enough for local-only use
Sign in to Ollama Account
If you want to use Ollama Cloud's online models, sign in to your account:
Click Sign In
In the Ollama settings window, click the "Sign in" button
Create or Sign In
- If you have an account, enter your email and password to sign in
- If you don't have an account, click "Create Account" to register
Verify Sign-In Status
After successful sign-in, the settings window will display your account information
Why sign in?
After signing in to your Ollama account, you can:
- Access online models on Ollama Cloud
- Sync your model list across multiple devices
- Favorite and manage your preferred models
Step 3: Connect OllaMan
Now, let's launch OllaMan and connect to the Ollama service.
Launch OllaMan
Double-click the OllaMan application icon to start the program.
Configure Server Connection
On first launch, OllaMan will automatically attempt to connect to the local Ollama service:
- At the top of the sidebar, you'll see the server selector
- The default server address is
http://localhost:11434 - If connected successfully, you'll see a green "Connected" status indicator
Connection Failed?
If it shows "Not Connected" status, please check:
- Confirm Ollama is running (verify by visiting http://localhost:11434)
- Confirm "Expose to network" option is enabled
- Try clicking "Test Connection" button to recheck
Multi-Server Management
You can add multiple Ollama servers:
Open Server Management
Click the server selector and choose "Manage Servers"
Add New Server
- Click the "Add Server" button
- Enter server name (e.g., "Office Server")
- Enter server URL (e.g.,
http://192.168.1.100:11434) - If required, enter authentication credentials (username and password)
Test and Save
Click "Test Connection" button, then click "Save" after successful connection
Step 4: Manage Models
After successful connection, let's start managing your AI models.
Browse Online Model Library
Go to Online Models Page
Click "Discover" (Online Models) option in the sidebar
Search for Models
Use the search box to find models you're interested in, such as:
llama3- Meta's latest large language modelmistral- High-performance open-source modelcodellama- Code generation specialist model
View Model Details
Click any model card to see detailed information:
- Model description and capabilities
- Available versions and parameter sizes
- Download counts and update time
Download Models
After finding the model you want, you can download it directly:
Select Version
On the model details page, choose the version that suits you:
- Larger parameters mean stronger capabilities but more space and memory usage
- Recommend starting with smaller versions (e.g., 7B)
Start Download
Click the "Pull" button next to the version
Monitor Download Progress
The download manager will automatically appear on the right side, showing real-time:
- Download progress percentage
- Current speed
- Estimated remaining time
View Local Models
Go to Local Models Page
Click "Installed" (Local Models) option in the sidebar
Browse Installed Models
You'll see all downloaded models, each card displays:
- Model name and tags
- Parameter size and quantization level
- Storage space and modification time
Manage Models
Each model card has action buttons:
- "Chat": Start conversation with the model
- "Delete": Remove unwanted models to free up space
Step 5: Start Chatting
Now, let's have your first conversation with an AI model!
Select a Model
From the local models list, click the "Chat" button on any model
Start Asking
Type Your Message
In the input box at the bottom of the page, type your question, for example:
- "Hello, please introduce yourself"
- "Write a bubble sort algorithm in Python"
- "Help me plan a weekend trip"
Send Message
- Press Enter to send the message
- Press Shift + Enter for a new line
View Response
The model will generate responses in real-time, you can see:
- Streaming text content
- Code highlighting and formatting
- Generation speed at the bottom (tokens/second)
Advanced Chat Features
Dashboard: Monitor System Status
Check system status anytime:
Access Dashboard
Click the "Dashboard" option in the sidebar
View Key Metrics
The dashboard displays real-time:
Model Statistics
- Total number of installed models
- Number of currently running models
Resource Usage
- Memory usage (VRAM)
- Disk space usage
Running Models
- Real-time display of active models
- Model expiration countdown
- One-click unload to free memory
Next Steps
Congratulations on completing the OllaMan quick start! Now you can:
Explore More Features
Learn about chat management, parameter tuning, shortcuts, and more advanced features
Model Recommendations
Discover AI models that best fit your needs
Need Help?
Get Support
- Visit full documentation for detailed features
- Join community discussions to share experiences
- Submit issues on GitHub for feedback
- Contact technical support for assistance
Enjoy using OllaMan!