---
title: "Can I run a large language model on my own computer?"
description: "Yes. A recent laptop with 16 GB of memory can run small models of about 7 to 14 billion parameters. A desktop with 64 to 128 GB can run models in the 70 to 120 billion range. The largest open models, from about 700 billion to over 2 trillion parameters, need hundreds of gigabytes or more and usually a cluster of machines."
url: https://exolabs.net/faq/can-i-run-an-llm-on-my-own-computer/
updated: 2026-10-26
---

# Can I run a large language model on my own computer?

Yes. A recent laptop with 16 GB of memory can run small models of about 7 to 14 billion parameters. A desktop with 64 to 128 GB can run models in the 70 to 120 billion range. The largest open models, from about 700 billion to over 2 trillion parameters, need hundreds of gigabytes or more and usually a cluster of machines.

Memory is the main limit. The whole model has to fit in fast memory (GPU memory, or unified memory on a Mac), with room left for the conversation context.

Speed depends mostly on memory bandwidth. A model that fits but runs at two words per second is not useful for daily work, so check both size and speed before you buy.

The quickest start is a desktop app such as exo, LM Studio or Ollama. You pick a model, it downloads, and you can chat with it or call it through a local API.

**Where exo fits:** If a model is too big for one machine, exo splits it across several. Two or four Macs connected with Thunderbolt can run models that no single desktop can hold.

Sources:
- [local.ai: which models fit your hardware](https://local.ai/)
- [exo on GitHub (README)](https://github.com/exo-explore/exo)

Page: https://exolabs.net/faq/can-i-run-an-llm-on-my-own-computer/ · Updated 2026-10-26 · Deployments: https://exolabs.net/#business (sales@exolabs.net)