Run Open Source LLM Locally: Easy 3-Step Guide with Kolosal AI

Tutorial - Jul 29, 2025

Ever wanted to run a powerful language model locally on your own PC? Good news — with open-source tools and Local AI models, it's totally possible. In this easy tutorial, we'll walk through how to run Gemma 3, an open source LLM, on a Windows computer using Kolosal AI. Kolosal AI is a lightweight app (only ~20 MB) that lets you run Local LLM models with no internet required. That means no cloud needed — everything runs offline on your device, keeping your data private and secure.

Step 1: Download Kolosal AI

Go to https://kolosal.ai and click the "Download for Windows" button. You'll get a small (~20 MB) KolosalAI_Installer.exe file. Kolosal supports both CPU and GPU by default.

Download Kolosal AI

Step 2: Install Kolosal AI

Double-click the installer to begin setup. If SmartScreen blocks it, click "More Info" → "Run Anyway". Complete the wizard like any typical Windows app.

Installer 1 Installer 2

Step 3: Load Gemma 3 and Start Chatting

Open Kolosal AI from your Start Menu. The app will open a clean UI — go to the Model Selector, find Gemma 3 (e.g., "Gemma 3 1B"), and click Download. Once downloaded, select it to load into memory.

Kolosal Model Manager

That's it! Now you can type prompts and chat with Gemma 3 — fully offline, right on your device.

Local AI Example

Try something like: "Suggest a unique pasta recipe using mushrooms and lemon."
Gemma 3 will generate a response like:

"Sure! How about a zesty Mushroom Lemon Herb Pasta? Start by sautéing mushrooms in olive oil with garlic..."

Gemma 3 response

Explore More Models

Kolosal AI supports many other open LLMs like Mistral, Qwen, and LLaMA. You can easily switch models, test responses, or run it as a local API server.