How to Install Ollama on Windows 10 (Step by Step for Beginners)

beginnerSoftware Install4 min
Independently tested and verified on Nov 18, 2026. Commands reproduced exactly as run.
Video thumbnail: How to Install Ollama on Windows 10 (Step by Step for Beginners)

Prerequisites

  • A computer running Windows 10
  • An internet connection to download Ollama and a model
  • A GPU is optional: Ollama falls back to the CPU

This tutorial takes about 4 minutes to complete.

This guide shows how to install Ollama on Windows 10 and run your first local AI model: download the installer, check the install in the Command Prompt, run Qwen 3.5 0.8B, check that it uses your GPU and chat in the Ollama app. It follows the video, so you can read each step here and watch it there.

Before you start

You need a computer running Windows 10 and an internet connection. A supported AMD or NVIDIA GPU makes models faster, but Ollama also runs on the CPU. The model used here, Qwen 3.5 0.8B, is small (about 1.2 GB).

Jump to a chapter in the video: Download · Install · Run a model · GPU and chat

Step 1: Download Ollama

Open your browser, go to ollama.com/download and click Download manually. When the download is finished, go to your Downloads folder and close the browser.

The Ollama download page with the Windows install and the Download manually link.

Step 2: Install Ollama

Double-click OllamaSetup and click Install. Ollama detects your GPU automatically (AMD or NVIDIA) and falls back to the CPU if there is none. When the install is done, click Continue. Cloud models need an Ollama account; to use Ollama locally, click No thanks.

The Downloads folder in File Explorer with the OllamaSetup file.

Step 3: Check the install in the Command Prompt

Type cmd in the search bar and run the Command Prompt as administrator, then click Yes. Check the installed version with ollama --version (this video shows version 0.40.16). Type ollama and press Enter to see the menu: the Ollama server is now running. Close the app, then open it again from the Start menu by clicking Ollama.

ollama --version
ollama

The Command Prompt after running ollama --version, which prints the installed version, and then ollama.

Step 4: Open the Ollama app and look at the models

Close the Command Prompt, click Apps in the left corner and then Chat. In the model list, anything with a cloud icon needs an account and anything with a download button is downloaded and run on your own machine. To find more models, go to ollama.com and click Models.

The Ollama app chat page with the model list open.

Step 5: Download and run a model

For this tutorial, download a small model: open the Qwen 3.5 page, scroll down to the qwen3.5:0.8b entry and click the copy icon. Open the Command Prompt again, type ollama run, paste the model name (ollama run qwen3.5:0.8b) and press Enter. When the download finishes, you can chat with the model in the Command Prompt, for example by asking why the sky is blue.

ollama run qwen3.5:0.8b

The Qwen 3.5 page on ollama.com with the list of model sizes, including qwen3.5:0.8b.

Step 6: Check that Ollama uses your GPU

To see whether Ollama uses your GPU, type device manager in the search bar, open Task Manager, click More details and choose the Performance tab, then select GPU. While the model answers you should see GPU activity. When you are done chatting, type /bye and press Enter, then close the window and Task Manager.

/bye

Task Manager on the Performance tab with the GPU selected while the model answers.

Step 7: Chat in the Ollama app and set the context length

You can also chat in the Ollama app: pick the model you downloaded (Qwen 3.5 0.8B appears in the list), start a new chat with the Chat button and use the + button to add documents or pictures; pictures need a vision model. In Settings, the context length controls how much the model remembers: the default of 4000 is too small for many tasks, so try 16K or 32K, but a longer context uses more VRAM. Click Chat and open your history to go back to an earlier chat.

FAQ

Download the installer from ollama.com/download, run OllamaSetup and click Install, then open the Command Prompt and check it with `ollama --version`.
No. You only need to sign up to use the cloud models; the models you download and run locally need no account.
Ollama detects a compatible AMD or NVIDIA GPU automatically and falls back to the CPU if there is none. In Task Manager, select GPU on the Performance tab to see it work.
The default of 4000 is too small for many tasks; try 16K or 32K in Settings, but a longer context uses more VRAM.
Type `/bye` and press Enter.

Never miss an issue

One email a week on local LLMs, DIY AI hardware, and the tools that power them. No spam — unsubscribe anytime.

Subscribe free

Products used in this tutorial

AMD Ryzen 9 9950X
cpu

AMD Ryzen 9 9950X

16-core, 32-thread AMD Ryzen 9 9950X desktop processor (Zen 5, AM5) with 5.7 GHz max boost and Radeon graphics — AMD's flagship mainstream CPU.

3 retailers
Gigabyte X870 Eagle WiFi 7
motherboard

Gigabyte X870 Eagle WiFi 7

AMD X870 ATX motherboard for AM5 with PCIe 5.0, DDR5, USB4, Wi-Fi 7 and 2.5GbE LAN — a modern foundation for Ryzen 9000-series desktop builds.

3 retailers
fanxiang S880R 1TB PCIe 4.0 NVMe SSD
storage

fanxiang S880R 1TB PCIe 4.0 NVMe SSD

fanxiang S880R 1TB PCIe 4.0 NVMe M.2 SSD with built-in heatsink — up to 7300MB/s reads and 3D TLC NAND for high-performance desktop and console storage.

2 retailers