Loading
AI systems
Run AI on Your Laptop for Free
Pick the Qwen size your laptop's RAM can actually run, install it with one command, then use it in the terminal and in VS Code with the Wi-Fi off.
Otomatic Guide by Natan Trolka
- Topic
- AI systems
- Reading time
- 7 min read
- Format
- Web and PDF
Most people install a local AI app, download the biggest model on the list, wait ninety seconds for a reply and decide local AI is not ready yet. The download was larger than the memory in the laptop, so the machine spent the whole time moving the model between RAM and disk instead of running it.
- Read your laptop's installed RAM and pick the Qwen size it can actually run.
- Install Ollama and hold a full conversation with the Wi-Fi switched off.
- Wire the same local model into VS Code through Continue, for chat and for autocomplete.
- Use the faster Apple silicon route on an M-series Mac, and know when to leave it alone.
One signup
Get the complete guide
Enter your details to unlock the full guide and get the PDF by email.
What the guide covers
Why the model size decides everything
Installing the app takes two minutes. The number you pick inside it is what makes local AI usable or useless.
Pick your Qwen size
8GB. Run ollama run qwen3.5:2b. About 2.7GB to download. If it still drags, drop to qwen3.5:0.8b at about 1GB.
Install it and run your first model
Roughly twenty minutes, most of which is the download.
Written by
Natan Trolka
Founder, Otomatic Digital
Natan builds AI systems for owner-led businesses in Ireland and the UK. Every guide here comes out of work that shipped for a client.
Before you enter your email
Start here
Have Otomatic build this for you.
The Otomatic Systems Audit is a free 30-minute conversation about your own workflow. You'll get a written roadmap within 24 hours, yours to keep whether you hire us or not.