Private Local Intelligence: Installing Ollama on Windows
Running artificial intelligence models locally on your PC ensures complete privacy and zero API costs. Ollama has emerged as the premier open-source tool for running large language models (like Llama 3.2, Qwen 2.5, and Phi-3) directly on Windows hardware. At Android People (androidpeople.in), we walk you through the complete setup process.
Step 1: Downloading the Windows Installer
Visit the official download portal at ollama.com and download the OllamaSetup.exe installer. Run the setup file to install the core background service into your user directory. Ollama automatically registers an icon in your Windows system tray, confirming that the local server engine is active.
Step 2: Pulling and Chatting with Llama 3.2 in Terminal
Launch Windows PowerShell or Command Prompt and execute your first model pull command:
ollama run llama3.2Ollama will automatically download the model weights, verify GPU availability (Nvidia CUDA or AMD ROCm), and open an interactive chat prompt directly in your console.
Customizing Model Storage Directory to Save C Drive Space
By default, downloaded model weights are saved on your C: drive. To move model storage to a secondary drive (e.g. D:\OllamaModels), open Windows System Properties, navigate to Environment Variables, create a new System Variable named OLLAMA_MODELS, and set its path value to your desired directory.
For more software tutorials and local AI guides, visit Android People.