Ollama lets you download and run large language models (LLMs) on your device.

Install Ollama on Arch Linux

1. Check whether your device has an AMD GPU, NVIDIA GPU, or no GPU. A GPU is recommended but not required.
2. Open Console, type only one of the following commands and press return. This may ask for your password but not show you typing it.

sudo pacman -S ollama-rocm    # for AMD GPU
sudo pacman -S ollama-cuda    # for NVIDIA GPU
sudo pacman -S ollama         # for no GPU (for CPU)

3. Enable the Ollama service [on-device and runs in the background] to start with your device and start it now.

sudo systemctl enable --now ollama

Test Ollama alone

1. Open localhost:11434 in a web browser and you should see Ollama is running. This shows Ollama is installed and its service is running.
2. Run ollama run deepseek-r1 in a console and ollama ps in another, to download and run the DeepSeek R1 model while seeing whether Ollama is using your slow CPU or fast GPU.

AMD GPU issue fix

https://lemmy.world/post/27088416

Use with Open WebUI

See this guide: https://lemmy.world/post/28493612