Running Ollama on Windows

By , Ready Utilities

Last updated: September 2026

Most troubleshooting content for Ollama on Windows assumes you're running it inside WSL2 with Docker. Most people don't need any of that. Here's the simple path, and the one install-order mistake that causes most "my GPU isn't being used" problems.

The simple path: you probably don't need WSL2

Ollama ships a native Windows installer that talks to your NVIDIA GPU directly through CUDA, with no Linux subsystem involved. If you just want to run ollama run commands in a terminal and chat with a model, downloading the installer from Ollama's official site and running it is the entire setup. WSL2 and Docker only come into play for more advanced cases: containerized deployments, some AMD GPU compatibility workarounds, or specific development workflows. If a guide's first step is "open WSL2," you've likely landed on content aimed at a more advanced setup than you need. See the beginner guide for the same install-to-first-chat steps that work here.

The install-order mistake

Ollama checks which GPU libraries are available at the moment it's installed. If you install Ollama before your NVIDIA drivers are fully set up, it won't know your GPU exists, and it'll quietly fall back to CPU, no error message. This is the single most common cause of "Ollama isn't using my GPU" on Windows.

The fix: make sure your NVIDIA driver is current first (check with nvidia-smi in a terminal, which should print your GPU's name and driver version), then install or reinstall Ollama after that's confirmed working.

Confirming your GPU is actually being used

After installing, run a model and check with:

ollama ps

If it shows the model running on CPU rather than GPU, that's the install-order issue above, or your GPU doesn't have enough VRAM for the model and Ollama is offloading part of it. Check the model's real memory requirement against your GPU in the hardware calculator before assuming it's a driver problem.

A note on AMD GPUs

NVIDIA has the smoothest path on Windows. AMD GPU support through ROCm is meaningfully less mature on native Windows; if you're on AMD and running into persistent issues, a Linux install tends to be more reliable for local AI work than continuing to fight Windows-specific AMD driver quirks. See the hardware guide's GPU tier table for more on this tradeoff.

The install-order behavior and GPU-detection troubleshooting steps are cross-checked against multiple current Ollama Windows/GPU troubleshooting guides (see the fact-check log). This page intentionally does not cover Docker or WSL2 setup, since that's a different, more advanced use case than most readers of this site need; it gets rechecked if Ollama's native Windows GPU detection behavior changes in a future release.

Sources

  1. InsiderLLM (opens in new tab)
  2. Serverman (opens in new tab)

Frequently asked questions

Do I need WSL2 to run Ollama on Windows?

No, not for basic use. The native Windows installer talks to your GPU directly. WSL2 is only relevant if you specifically need Docker-based deployment or certain AMD compatibility workarounds.

Why isn't Ollama using my GPU on Windows?

The most common cause is installing Ollama before your NVIDIA drivers were fully set up. Confirm your driver works with nvidia-smi, then reinstall Ollama. The second most common cause is a model too large for your VRAM, which the hardware calculator can check.

Does AMD work as well as NVIDIA for local AI on Windows?

Not currently. AMD's ROCm support is less mature on native Windows than NVIDIA's CUDA path. If you're on AMD and hitting persistent issues, Linux tends to be more reliable for this specific use case.