What you get
You get a Qwen model on your laptop that answers in the terminal and in VS Code with the Wi-Fi off. The table below matches the model to your RAM, so your first download is one the machine can run.
Match a Qwen model to your laptop's RAM, install it with one command, and use it offline in the terminal and in VS Code.
Otomatic Guide by Natan Trolka
A common first attempt at local AI downloads the biggest model on the list and waits ninety seconds for a reply. The model was larger than the laptop's memory, so the machine spent the wait swapping it between RAM and disk.
Enter your details to unlock the full guide and get the PDF by email.
You get a Qwen model on your laptop that answers in the terminal and in VS Code with the Wi-Fi off. The table below matches the model to your RAM, so your first download is one the machine can run.
You get a Qwen model on your laptop that answers in the terminal and in VS Code with the Wi-Fi off. The table below matches the model to your RAM, so your first download is one the machine can run.
8GB. ollama run qwen3.5:2b (about 2.7GB). Still slow: qwen3.5:0.8b (about 1.3GB).
Get it from Files in this guide, at the end: every command and the Continue config in one file.
Written by
Natan Trolka
Founder, Otomatic Digital
Natan founded Otomatic and leads its commercial strategy and client relationships. Otomatic builds and manages AI systems for established, owner-led businesses in Ireland, the UK and the US. Every guide here comes out of methods he runs in his own business or that Otomatic has built for clients.
The Free Business Check is a 30-minute call on your business priorities and bottlenecks. Then your AI Recommendation Plan, yours whether you hire us or not.
Starts with a 30-minute Business Check and your AI Recommendation Plan.