How to Install Ollama on Ubuntu 26.04 (Step by Step for Beginners)

beginnerSoftware Install6 min
Independently tested and verified on Nov 20, 2026. Commands reproduced exactly as run.
Video thumbnail: How to Install Ollama on Ubuntu 26.04 (Step by Step for Beginners)

Prerequisites

  • A computer running Ubuntu 26.04
  • An internet connection
  • Your account password, which sudo asks for
  • A graphics card (NVIDIA, AMD or Intel) for faster answers, or a CPU only

This tutorial takes about 6 minutes to complete.

This guide shows how to install Ollama on Ubuntu 26.04, set up your graphics card for NVIDIA, AMD or Intel, manage the Ollama server and run your first model. It follows the video, and every command below is the one typed on screen, ready to copy.

Before you start

You need a computer running Ubuntu 26.04, an internet connection and your account password: the install commands ask for it. A graphics card is optional: if you run on a CPU, skip the GPU section and go straight to the install script in Step 3.

Jump to a chapter in the video: Update and install curl · GPU drivers · Install Ollama · Manage the server · Run a model and commands

Step 1: Update Ubuntu and install curl

Open a terminal. Update your package list, then install curl, which downloads the Ollama install script.

sudo apt update
sudo apt install curl -y

The terminal installing curl with the sudo apt install curl -y command.

Step 2: Set up your GPU drivers

Do this before you run the Ollama installer, so Ollama can bind to your hardware without display conflicts or black screens. The setup depends on your GPU. The video uses an NVIDIA RTX 5060 Ti 16 GB.

NVIDIA

For RTX 20, 30, 40 and 50 series cards, install the open driver:

sudo apt install nvidia-driver-595-open -y

The terminal with the sudo apt install nvidia-driver-595-open -y command typed for RTX 20, 30, 40 and 50 series cards.

For GTX 10 series and 16 series cards, use sudo apt install nvidia-driver-595 -y instead, then reboot your system.

AMD

Ubuntu 26.04 includes up-to-date open source AMD GPU kernel drivers, but you must give your user account access to the hardware by adding it to the render and video groups so Ollama can talk to the GPU. Run sudo usermod -aG render,video $USER, then reboot your computer. This works for RX 6800 cards and newer, which Ollama auto-detects.

Intel (Arc and Core Ultra iGPU)

Ollama uses Vulkan as the backend on Intel GPUs, so install the Vulkan drivers with sudo apt install mesa-vulkan-drivers vulkan-tools -y and set the permissions with sudo usermod -aG render,video $USER. Then reboot your computer.

Check the NVIDIA driver

After the reboot, open a terminal and run the command below. It lists your GPU, which means the driver is installed.

nvidia-smi

The terminal after running nvidia-smi, which lists the NVIDIA GPU and the driver version.

Step 3: Install Ollama

Open your browser, go to ollama.com/download/linux, select Linux and copy the curl command.

The Ollama download page at ollama.com/download/linux with the Linux install command in the browser.

Close the browser, paste the command into the terminal and press Enter. Enter your password and the installation starts automatically.

curl -fsSL https://ollama.com/install.sh | sh

The terminal after running the Ollama install script curl -fsSL https://ollama.com/install.sh | sh, which ends with the NVIDIA GPU detected message.

When it finishes, check the installed version:

ollama --version

The terminal after running ollama --version, which shows the installed Ollama version.

Step 4: Manage the Ollama server

Ollama runs as a background service. Check its status with the first command; it shows active (running). Press Ctrl+C to exit the status view.

sudo systemctl status ollama

The terminal after running sudo systemctl status ollama, which shows the Ollama service as active (running).

To stop the server, run the stop command and check the status again: it now shows inactive (dead).

sudo systemctl stop ollama
sudo systemctl status ollama

The terminal after running sudo systemctl stop ollama and checking the status again, which now shows the service as inactive (dead).

To start it again, run the start command and check the status: it is active (running) again.

sudo systemctl start ollama
sudo systemctl status ollama

The terminal after running sudo systemctl start ollama, which shows the Ollama service as active (running) again.

Clear the screen and show the server address with this command:

clear
sudo ss -tulpn | grep ollama

Step 5: Run your first model

Open your browser, go to the Ollama website, click Models and copy the name of the model. The video uses Qwen 3.5 0.8B.

The Ollama models page in the browser, where you copy the model name.

Run it. Ollama downloads the model and opens a chat. Ask a question, then type /bye to exit the chat.

ollama run qwen3.5:0.8b

The terminal after running ollama run qwen3.5:0.8b, with the model loaded and a chat prompt ready.

To see the timing data at the end of every response, add the verbose flag:

ollama run qwen3.5:0.8b --verbose

The terminal after running ollama run qwen3.5:0.8b --verbose, with the timing statistics at the end of the answer.

Ollama commands to know

  • ollama ls lists the models you have downloaded on your computer.
  • ollama ps lists the models loaded into VRAM and shows whether they use the GPU or the CPU. The video shows 100% GPU.
  • ollama rm qwen3.5:0.8b deletes a model: type ollama rm and the model name.
  • ollama stop qwen3.5:0.8b unloads the model from memory: type ollama stop and the model name.
  • ollama help lists all the commands.
ollama ls
ollama ps

The terminal after running ollama ls, which lists the downloaded models.

The terminal after running ollama ps, which shows the loaded model and that it runs on the GPU.

Ollama on Linux does not come with a GUI. In the next tutorial the video connects it to a GUI application called Open WebUI, which gives you a chat interface where you can chat with your documents and upload pictures.

FAQ

Install curl with `sudo apt install curl -y`, set up your GPU drivers, then run `curl -fsSL https://ollama.com/install.sh | sh` and check the install with `ollama --version`.
For RTX 20, 30, 40 and 50 series cards run `sudo apt install nvidia-driver-595-open -y`. For GTX 10 and 16 series cards run `sudo apt install nvidia-driver-595 -y`. Reboot, then check it with `nvidia-smi`.
Ubuntu 26.04 already includes the open source AMD drivers. Add your user to the render and video groups with `sudo usermod -aG render,video $USER` and reboot. Ollama auto-detects RX 6800 cards and newer.
Ollama uses Vulkan on Intel Arc and Core Ultra iGPUs. Install the Vulkan drivers with `sudo apt install mesa-vulkan-drivers vulkan-tools -y`, add your user to the render and video groups and reboot.
Run `ollama ps`. It lists the models loaded into VRAM and shows whether they use the GPU or the CPU.
No. Ollama on Linux runs in the terminal and has no GUI. The next tutorial connects it to a GUI application called Open WebUI.

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