How to Install Ollama on Windows [Guide]

Here is the Guide How to Intall Ollama on Windows.

✅ Requirements:

• Windows 10/11 (64-bit)
• At least 8 GB RAM (16 GB+ recommended)
• CPU-only works fine (though some models are faster on GPU, GPU support is still limited on Windows)
• WSL2 (Windows Subsystem for Linux) is required (Ollama installs it automatically)

🪜 Step-by-Step Installation

1. Download Ollama
   • Go to: https://ollama.com/
   • Click Download for Windows
2. Install Ollama
   • Run the installer.
   • It will set up WSL2 automatically if you don’t have it.
   • Follow the prompts (restarts may be required).
3. Open Terminal (CMD, PowerShell, or Windows Terminal)
   • You can now run commands like:

ollama run llama2

✅ Done! It will download the model (e.g. LLaMA 2) and run it locally.

🧪 Try Other Models

After installation, you can run other models like:

ollama run mistral
ollama run gemma
ollama run codellama
ollama run orca-mini

Full model list here: https://ollama.com/library

🔥 1. Open WebUI for Ollama (ollama-webui)

This is a popular project built with [Node.js + React] and connects directly to Ollama’s local API.

✅ Easy Way to Run It:

Option A: Use Ollama WebUI by Open WebUI

This one’s plug-and-play:

👉 GitHub: https://github.com/open-webui/open-webui

🚀 Steps:

1. Make sure Ollama is installed and running:

ollama run mistral  # or just `ollama serve`

Install Docker (if you don’t have it):

Download Docker Desktop

Run Open WebUI using Docker:

docker run -d \
  -p 3000:3000 \
  -e 'OLLAMA_BASE_URL=http://host.docker.internal:11434' \
  --name open-webui \
  ghcr.io/open-webui/open-webui:main

Open in Browser:

Go to: http://localhost:3000

You’ll now see a ChatGPT-like interface connected to Ollama!