How to Run Ollama Models Locally: Windows & Linux Tutorial (2025 Guide).

Installing Ollama on Windows

 Go to Ollama Website and download for Windows

Download Ollama on Windows

And Install Just like any other software 

Installing Ollama on Linux

---

Run The following command:

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

 This command will install the Ollama service on your machine

Verifying the Install

Run The following command:

>> ollama --version

Searching For Models

You can search for Models from Ollama Model Search

Here you can see the list of all the Models Available

You can select the Model of you choice

Installing Models

>> ollama run gemma3

Usage with Python

>> ollama pull gemma3

Then install Ollama’s Python library:

>> pip install ollama

Python Program to chat with model

from ollama import chat
from ollama import ChatResponse

response: ChatResponse = chat(model='gemma3', messages=[
  {
    'role': 'user',
    'content': 'Why is the sky blue?',
  },
])
print(response['message']['content'])
# or access fields directly from the response object
print(response.message.content)

Usage with Javascript

>> ollama pull gemma3

Then install Ollama’s JavaScript library:

>> npm i ollama

JavaScript Program to chat with model

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'gemma3',
  messages: [{ role: 'user', content: 'Why is the sky blue?' }],
})
console.log(response.message.content)

Allowing Ollama Access from External Network in Windows

• Open the Control Panel.
• Click System and Security, then System
• Click Advanced system settings on the left
• Inside the System Properties window, click the Environment Variables… button.

Create a New Environment variable

OLLAMA_HOST = 0.0.0.0  # configure any interface or IP of your choice

0.0.0.0 allows Access from any Interface

You can choose to allow from any specific interface

OPTIONAL to change the Listening PORT you can rather use following code

here we have changed the port from 11434 to 12345  you can choose any port

OLLAMA_HOST = 0.0.0.0:12345

Security Note:  "Warning: Binding to 0.0.0.0 exposes the API publicly—use firewall (e.g. allow from 192.168.1.0/24 to any port 11434 on windows) or restrict to localhost (127.0.0.1) for production."

Allowing Ollama Access from External Network in Linux

To Set the OLLAMA_HOST Variable in Linux

sudo systemctl edit ollama

Alternatively, create an override file manually in 

/etc/systemd/system/ollama.service.d/override.conf

Now Enter and save the Following

[Service]
Environment="OLLAMA_HOST=0.0.0.0"

OPTIONAL to change the Listening PORT you can rather use following code

here we have changed the port from 11434 to 12345  you can choose any port

[Service]
Environment="OLLAMA_HOST=0.0.0.0:12345"

0.0.0.0 allows Access from any Interface

You can choose to allow from any specific interface

Now reload the daemon and restart the Ollama service

>> sudo systemctl daemon-reload
>> sudo systemctl restart ollama.service

To verify you can use command 

>> ss -lt | grep 11434

Security Note:  "Warning: Binding to 0.0.0.0 exposes the API publicly—use firewall (e.g., ufw allow from 192.168.1.0/24 to any port 11434 on Ubuntu) or restrict to localhost (127.0.0.1) for production."