Running large language models locally
Model Shop
Image © sdecoret, 123RF.com
Ollama and Open WebUI let you join the AI revolution without relying on the cloud.
Large language models (LLMs) such as the ones used by OpenAI's [1] ChatGPT [2] are too resource intensive to run locally on your own computer. That's why they're deployed as online services that you pay for. However, since ChatGPT's release, some significant advancements have occurred around smaller LLMs. Many of these smaller LLMs are open source or have a liberal license (see the "Licenses" box). You can run them on your own computer without having to send your input to a cloud server and without having to pay a fee to an online service.
Because these LLMs are computationally intensive and need a lot of RAM, running them on your CPU can be slow. For optimal performance, you need a GPU – GPUs have many parallel compute cores and a lot of dedicated RAM. An NVIDIA or AMD GPU with 8GB RAM or more is recommended.
In addition to the hardware and the models, you also need software that enables you to run the models. One popular package is Ollama [3], named for Meta AI's large language model Llama [4]. Ollama is a command-line application that runs on Linux, macOS, and Windows, and you can also run it as a server that other software connects to.
[...]
Buy this article as PDF
(incl. VAT)
Buy Linux Magazine
Subscribe to our Linux Newsletters
Find Linux and Open Source Jobs
Subscribe to our ADMIN Newsletters
Digital Autonomy
• The Answer Was Already on the Shelf
• Changing the Chip Industry: How Public Investment Has Grown Open Silicon
• United Nations Open Source Portal Goes Live
• EU Open Source Strategy Plays Key Role in Tech Sovereignty Package
• France Says “Au Revoir” to Microsoft
Support Our Work
Linux Magazine content is made possible with support from readers like you. Please consider contributing when you’ve found an article to be beneficial.
News
-
Dutch Government Turns to Open Source for Digital Sovereignty
Following in the footsteps of European countries, the Netherlands is looking to increase its sovereign digital infrastructure with open source software.
-
Linux May Soon Work on Snapdragon X2-Based PCs
If you're thinking about buying a Snapdragon X2-based desktop or laptop, Linux may soon be an option.
-
KDE for People Initiative Calls for AI Ban in Plasma
A new community of KDE wants the project to adopt a strict no-AI policy for KDE Plasma.
-
KDE Sets Ambitious Goals for 2026 and Beyond
KDE Connect reveals the goals for the Linux desktop darling, with one of those goals long overdue.
-
It’s Time to Test Fedora 45 Beta
Fedora 45 beta has been released with updated Gnome, KDE Plasma, and kernel.
-
Ubuntu Stonking Stingray Gets Even Rustier
Ubuntu 26.10 has completed its migration to the Rust-based coreutils.
-
AI Fixes Linux Bottlenecks Using “Hideous” Code
A Linux developer used AI to fix bottlenecks that caused problems when building the kernel. The resulting AI-generated code needed a lot of work.
-
Advanced Video Coding Still Under Patent
Brazilian patent BRPI0109962B1 has expired, which means that DivX and Xvid are no longer problematic for Linux, but it doesn’t mean that video is all of a sudden fully unleashed.
-
2,000 Vulnerabilities per Linux Release
Thanks to AI bug hunters, the Linux kernel is seeing record numbers of vulnerabilities, and it's overwhelming developers.
-
Linux Exempt from California’s Age Verification Law
So long as Linux is distributed under the GPL, MIT, BSD, and Apache licenses, the OS is exempt from being required to verify the age of its users in California.