Browse categories
Explore
Fiverr Pro
English
$
USD
I will deploy a self hosted ai stack with openwebui and ollama on your vps
Said E
Level 2
About this gig
Need your own private AI server?
I will deploy a complete self-hosted AI stack on your VPS using OpenWebUI, Ollama, Qdrant, LiteLLM, SearXNG, CrewAI and supporting infrastructure.
Run powerful local LLMs securely on your own server with full control over your data, models, users and integrations.
What gets deployed:
Nginx Proxy Manager, Portainer, Vaultwarden
Ollama, OpenWebUI, LiteLLM, Qdrant, SearXNG, CrewAI
Basic $90 Full 9-service stack, custom domain, SSL, tested and ready
Standard $130 Adds n8n automation, Uptime Kuma monitoring, automated backup
Premium $200 Adds Keycloak SSO, role-based access control, one login for everything
Every package includes:
- Docker Compose architecture clean and maintainable
- Custom domain + SSL via Let's Encrypt
- End-to-end testing before delivery
- Setup documentation for your deployment
- Post-delivery support up to 14 days
Requirements: VPS with 8GB+ RAM, Ubuntu 24.04 or AlmaLinux 9, SSH root access, subdomains mapped to server IP.
Not sure your server qualifies? Message me first I'll confirm in minutes.
Your server. Your data. Your AI.
Get to know Said E
Said E
Linux Server and Automation Expert
Level 2
- FromMorocco
- Member sinceOct 2014
- Avg. response time1 hour
- Last delivery2 days
Languages
English, Arabic, French
With over 10 years of experience in IT management, cloud computing, Linux server administration, and web hosting, I specialize in setting up and managing reliable, high-performance environments for businesses and developers.
I offer professional services including:
CWP (CentOS Web Panel) installation and optimization
Server hardening and VPS management
WordPress installation, migration, and optimization
Self-hosted automation tools like n8n, Metabase, and others
Custom PHP script installation and troubleshooting
I’m also highly familiar with platforms like AWS, DigitalOcean, Contabo and others
My Portfolio
Other AI Development Services I Offer
FAQ
Which AI models can I run?
Any model supported by Ollama — Llama 3, Mistral, DeepSeek, Gemma, Phi, Qwen and more. I'll recommend the best fit based on your server RAM.
I already have services running on my VPS. Will this break anything?
Not if we talk first. Message me before ordering with your current setup and I'll confirm compatibility.
Can I add more services after delivery?
es. The Docker Compose architecture is built to scale. Adding new services is straightforward and I can assist anytime.
Is my data actually private?
100%. Everything runs on your server. Nothing touches external APIs unless you choose it. That's the whole point.
Do you offer ongoing maintenance?
Yes. Message me after delivery for a custom monthly maintenance package tailored to your stack.
How much RAM do I need?
8GB: small models and testing / 16GB: recommended for most deployments / 32GB+: larger models and multiple users. Not sure? Send me your specs.
