- Install WSL.
- Install Docker for Desktop and ensure it is enabled for WSL
- Open terminal as an administrator and open a tab for WSL
- Install Nvidia Container Toolkit if needed for a Nvidia GPU & configure it.
- Run
docker pull ollama/ollama
- Run the following:
docker run -d \
--gpus all \
-v ollama:/root/.ollama \
-p 11434:11434 \
--security-opt=no-new-privileges \
--cap-drop=ALL \
--cap-add=SYS_NICE \
--memory=8g \
--memory-swap=8g \
--cpus=4 \
--read-only \
--name ollama \
ollama/ollama
- If a popup comes up for firewall permissions, click
Allow
- Check to see if docker is running with
docker ps to ensure its running
- Run the following command to run DeepSeek
docker exec -it ollama ollama run deepseek-r1
- Once the model is ready the prompt will change to ask for a message.
- Once done, find the Container ID with
docker ps and then run docker stop <containerID>