<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/llamagpt---a-self-hosted-offline-chatgpt-2wiolcgpq" -->

---
title: LlamaGPT - A Self-Hosted, Offline, ChatGPT | daily.dev
description: LlamaGPT is a self-hosted chatbot powered by Llama 2 that works offline, ensuring 100% privacy. It supports Code Llama models and NVIDIA GPUs. Minimum system...
canonical: https://daily.dev/posts/llamagpt---a-self-hosted-offline-chatgpt-2wiolcgpq
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: LlamaGPT - A Self-Hosted, Offline, ChatGPT | daily.dev
og:description: LlamaGPT is a self-hosted chatbot powered by Llama 2 that works offline, ensuring 100% privacy. It supports Code Llama models and NVIDIA GPUs. Minimum system...
og:url: https://daily.dev/posts/llamagpt---a-self-hosted-offline-chatgpt-2wiolcgpq
og:image: https://api.daily.dev/og/posts/2wIoLCgPQ.png
og:image:alt: LlamaGPT - A Self-Hosted, Offline, ChatGPT
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# LlamaGPT - A Self-Hosted, Offline, ChatGPT

**[Noted](https://daily.dev/sources/noted)** · [@noted](https://daily.dev/noted) · 4 min read · 232 upvotes · 12 comments

## Summary

LlamaGPT is a self-hosted chatbot powered by Llama 2 that works offline, ensuring 100% privacy. It supports Code Llama models and NVIDIA GPUs. Minimum system requirements and a list of supported models are provided.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://noted.lol/llamagpt/>

## Community discussion

Top comments from developers on daily.dev.

**@varagos** · 5 upvotes

> This is very interesting but you need a really high end setup to start getting some barely acceptable times per prompt.

**@techfoutraque** · 1 upvotes

> Along the same lines, I came across this tool: https://github.com/lllyasviel/Fooocus.
> Not yet tested, but it seems to require fewer resources.

**@pife00** · 1 upvotes

> Shoot, I use AMD

**@aksabar\_\_** · 0 upvotes

> The response time is going to be 1 light year if you dont have a high end device.

**@saschar** · 0 upvotes

> MPS wen

## Similar posts on daily.dev

- [Don’t just attend KubeCon \+ CloudNativeCon, Merge Forward your experience\!](https://daily.dev/posts/don-t-just-attend-kubecon-cloudnativecon-merge-forward-your-experience--l0rpp73x8) · CNCF · 1 upvotes · 0 comments
- [Announcing H2 2026 KCDs](https://daily.dev/posts/announcing-h2-2026-kcds-m96goajm1) · CNCF · 1 upvotes · 0 comments
- [Two months of Open Community Groups](https://daily.dev/posts/two-months-of-open-community-groups-asf52zhbs) · CNCF · 0 upvotes · 0 comments
- [CNCF Unveils Schedule for KubeCon \+ CloudNativeCon Europe 2026](https://daily.dev/posts/cncf-unveils-schedule-for-kubecon-cloudnativecon-europe-2026-ikhcoa5cb) · CNCF · 2 upvotes · 0 comments
- [CNCF Debuts KubeCon \+ CloudNativeCon Japan 2026 Schedule](https://daily.dev/posts/cncf-debuts-kubecon-cloudnativecon-japan-2026-schedule-xp5pyudub) · CNCF · 1 upvotes · 0 comments

---

Tags: [#ai](https://daily.dev/tags/ai), [#chatgpt](https://daily.dev/tags/chatgpt), [#docker-compose](https://daily.dev/tags/docker-compose)

[View this post on daily.dev](https://daily.dev/posts/llamagpt---a-self-hosted-offline-chatgpt-2wiolcgpq)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"LlamaGPT - A Self-Hosted, Offline, ChatGPT","url":"https://daily.dev/posts/llamagpt---a-self-hosted-offline-chatgpt-2wiolcgpq","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/llamagpt---a-self-hosted-offline-chatgpt-2wiolcgpq"},"datePublished":"2023-10-07T18:03:53.308Z","dateModified":"2023-10-08T15:00:06.772Z","description":"LlamaGPT is a self-hosted chatbot powered by Llama 2 that works offline, ensuring 100% privacy. It supports Code Llama models and NVIDIA GPUs. Minimum system...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/ae746406c2b214f63460878fefccd627?_a=AQAEufR","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/ae746406c2b214f63460878fefccd627?_a=AQAEufR","isAccessibleForFree":true,"articleSection":"Noted","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Person","name":"Jeremy","url":"https://daily.dev/noted","image":"https://media.daily.dev/image/upload/f_auto/v1650038055/avatars/Ep4ZyI0wF3cWNWXQjc2m1","description":"Hey there! 👋 I'm Jeremy, creator of Noted.lol. I'm a Self Hosting and Homelab autodidact!","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":2590}},"commentCount":12,"discussionUrl":"https://daily.dev/posts/llamagpt---a-self-hosted-offline-chatgpt-2wiolcgpq","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":232},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":12}],"keywords":"ai,chatgpt,docker-compose","timeRequired":"PT4M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Noted","item":"https://daily.dev/sources/noted"},{"@type":"ListItem","position":3,"name":"LlamaGPT - A Self-Hosted, Offline, ChatGPT"}]}
{"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/llamagpt---a-self-hosted-offline-chatgpt-2wiolcgpq","comment":[{"@type":"Comment","text":"This is very interesting but you need a really high end setup to start getting some barely acceptable times per prompt.","datePublished":"2023-10-12T06:29:40.631Z","url":"https://daily.dev/posts/2wIoLCgPQ#c-E8Blcl9Qd","author":{"@type":"Person","name":"Markos Girgis","url":"https://daily.dev/varagos","image":"https://avatars.githubusercontent.com/u/63424729?v=4"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":5}},{"@type":"Comment","text":"Along the same lines, I came across this tool: https://github.com/lllyasviel/Fooocus.\nNot yet tested, but it seems to require fewer resources.","datePublished":"2023-11-06T21:16:25.487Z","url":"https://daily.dev/posts/2wIoLCgPQ#c-89lp0kdB2","author":{"@type":"Person","name":"Tech Foutraque","url":"https://daily.dev/techfoutraque","image":"https://media.daily.dev/image/upload/s--mYz5lcBp--/f_auto,q_auto/v1701433930/avatars/avatar_SrmmsL7PPgDrJaX1lefPq"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1}},{"@type":"Comment","text":"Shoot, I use AMD","datePublished":"2023-10-25T22:21:00.179Z","url":"https://daily.dev/posts/2wIoLCgPQ#c-Nn67JNovc","author":{"@type":"Person","name":"FELIPE PENA M","url":"https://daily.dev/pife00","image":"https://lh3.googleusercontent.com/a/ACg8ocIgrNEr9H7LOe756LDztMpn_qPR0pxMJhAWAE4risc0Bg=s96-c"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1}},{"@type":"Comment","text":"The response time is going to be 1 light year if you dont have a high end device.","datePublished":"2023-10-29T15:00:37.421Z","url":"https://daily.dev/posts/2wIoLCgPQ#c-pNhWLnFMF","author":{"@type":"Person","name":"Amit Kumar Sahoo","url":"https://daily.dev/aksabar__","image":"https://lh3.googleusercontent.com/a-/AOh14GjLdo_Fw2NVjK94efZRR2lJ1aEN-aKIb6XK37DZYg=s100"}},{"@type":"Comment","text":"MPS wen","datePublished":"2023-11-26T15:14:11.368Z","url":"https://daily.dev/posts/2wIoLCgPQ#c-BAVCV3pf2","author":{"@type":"Person","name":"SaschaR","url":"https://daily.dev/saschar","image":"https://lh3.googleusercontent.com/a/ACg8ocIwYFNpykKVvoECV3ZFM_zErXyoY-WNi9u_LVL9hHvTuh5M=s96-c"}}]}
```

