---
title: "Discussion on \"🚀 Deploy Ollama on AWS EC2 (GPU) and Connect It to VS Code (Continue Extension)\" | Hashnode"
description: "Discussion on \"🚀 Deploy Ollama on AWS EC2 (GPU) and Connect It to VS Code (Continue Extension)\". Self-hosting your own Large Language Model (LLM) gives you:\n\n✅ Full control over models\n\n✅ No per-token billing\n\n✅ Private AI infrastructure\n\n✅ Direct IDE integration\n\n\nIn this guide, we’ll:\n\nDeploy O"
url: "https://hashnode.com/posts/deploy-ollama-on-aws-ec2-gpu-and-connect-it-to-vs-code-continue-extension/69ad542086766ac3a6240eed"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [🚀 Deploy Ollama on AWS EC2 (GPU) and Connect It to VS Code (Continue Extension)](https://aws-deployments.hashnode.dev/deploy-ollama-on-aws-ec2-gpu-and-connect-it-to-vs-code-continue-extension?utm_source=hashnode&utm_medium=feed)

Self-hosting your own Large Language Model (LLM) gives you: ✅ Full control over models ✅ No per-token billing ✅ Private AI infrastructure ✅ Direct IDE integration In this guide, we’ll: Deploy O

Mar 8 · 4 min read · aws-deployments.hashnode.dev  
Read the article

## Written by

[Harish Narnaware](https://hashnode.com/@harish343)

@harish343 · India

  
[View profile](https://hashnode.com/@harish343)

Devops Enginner

I am here for giving wonderful knowledge to society

## Responses

Markdown supported · ⌘↵ to post

No responses yet.