---
title: "Large Language Models"
description: "A brief post on the current state of large language models and the potential of self-hosting them on consumer hardware!"
date: 2023-03-13
url: https://krismuniz.com/posts/large-language-models
---

# Large Language Models

It is no secret that I've been very enthusiastic about _The Commercial NLP Renaissance_ a.k.a. Large Language Models (yet [a bit skeptical about the type of people its attracting](https://twitter.com/KristianMuniz/status/1627921607120556032)).

I've been building a lot of stuff with them, mainly [Printloop](https://printloop.dev), but also [BORI](https://github.com/krismuniz/bori).

This week is expected to be big for language models as GPT-4 is rumored to be announced, but also high-performance language models are very close to land in consumer hardware!

## Language Computer

I've been looking for ways to build a "Language Computer" for my home; I want to run a service on my own hardware that I can use to build personal language tools, services, and home automation workflows.

I also want to host other AI services at home (like speech-recognition), but my focus is on language models first because I believe it's the most useful.

Turns out, I am very close to making this a reality! We'll soon be able to run a language model with performance comparable to OpenAI's Davinci GPT models on our own hardware.

I highly recommend reading Simon Wilson's ["Stanford Alpaca" post](https://simonwillison.net/2023/Mar/13/alpaca/) discussed the acceleration of large language model development on-device, particularly talking about Stanford Alpaca and llama.cpp.

I already so many ideas for things I will be able to do with my own language service at home:

- Digitize, summarize, categorize, and sort my snail mail
- Digest, summarize, and present the news to me
- An army of mechanical historians that indefinitely browse the web, recording findings about topics that I am interested in, keeps track of trends, and writes me a report every day