Browse categories
Explore
Fiverr Pro
English
$
USD
I will set up a private self hosted llm on your server with ollama, vllm, open webui
Junaid Aslam
Level 1
Vetted by Fiverr Pro
Junaid Aslam was selected by the Fiverr Pro team for their expertise.
About this gig
Please message me to discuss requirements before placing the order.
Want an AI assistant that keeps your data on your own server? I set up a private LLM on your VPS or GPU server. No prompt or document goes to a third party.
What I set up
- Ollama or vLLM serving an open model: Llama 3, Mistral, DeepSeek, Qwen, Gemma, or any Hugging Face model
- Open WebUI as the chat screen, with user accounts and roles
- An OpenAI-compatible API, so your apps call it like they call OpenAI
- Optional RAG on your PDFs and documents, with pgvector or Qdrant
- Docker Compose setup, Nginx, HTTPS, and a written handover guide
Where it runs
Any Linux server: your VPS, on-premises machine, AWS, Azure, Google Cloud, or a rented GPU on RunPod. GPUs: NVIDIA H100, A100, L40S, RTX 4090. I tell you the monthly cost first.
Data location
I can host in the EU, UK, US or any country or region you choose. This supports data residency rules such as GDPR, UK GDPR, and CCPA.
What I do not do
I do not fine-tune or quantize models. I deploy and connect existing open models.
Before placing the order
Let's discuss your document type, number of users, and budget. Then I recommend a model and a server size.
Get to know Junaid Aslam
Junaid Aslam
ASP Dot NET Core, Web API, React, JS, TS, SQL, NoSQL, AWS, Azure, AI Chatbot RAG
Level 1
Junaid Aslam is part of the Fiverr Pro catalog and has been hand-picked by a dedicated Fiverr Pro team for their skills and expertise.
Vetted for
Software Development
- FromPakistan
- Member sinceSep 2015
- Avg. response time1 hour
- Last delivery1 month
Languages
Urdu, English
Pro-vetted Senior .NET engineer with 7+ years building full-stack web apps and APIs for clients across the US, UK, EU, and beyond. I specialise in .NET, .NET Core, ASP.NET MVC5, Web API, Blazor, React, and Next JS, following Clean Architecture and SOLID principles so your codebase stays maintainable as it grows. I also offer AI automation & AI integration services, including custom AI chatbots, RAG, n8n, make.com AI workflows, Claude/GPT API.. My tech stack includes C# .NET 10, 9.0 · Blazor · EF Core · API · React/Next.js · TypeScript · MS SQL · Azure · AWS · WordPress · Firebase · PostgreSQL.
My Portfolio
Other AI Development Services I Offer
FAQ
Do I need my own server or GPU?
No. I can set it up on a VPS, your cloud account, or a rented GPU on RunPod. I tell you the size and monthly cost before I start. You pay the provider directly.
Which servers and GPUs can you use?
Any Linux server with SSH access: AWS, Azure, Google Cloud, RunPod, or your own hardware. GPUs include NVIDIA H100, A100, L40S, and RTX 4090.
Which open LLMs can you run?
Llama 3, Mistral, DeepSeek, Qwen, and Gemma, in the sizes your hardware supports. I help you pick the best model for your use
Is my data private?
Yes. The model runs on your server. No prompt or document goes to an outside AI service unless you ask me to connect one.
Ollama or vLLM, which one do I need?
Ollama is simple and good for small teams. vLLM is faster for many users on a GPU. I recommend one after you tell me your user count.
Can my app call it like the OpenAI API?
Yes. Ollama and vLLM both offer an OpenAI-compatible API. Your apps change only the base URL and model name.
Can it answer from my own documents (RAG)?
Yes, in the Premium package. I add RAG on your PDFs and files with pgvector or Qdrant.
Can you host in the EU, UK, or US for GDPR?
I can host in the region you choose. This supports data residency rules such as GDPR, UK GDPR, and CCPA. I do not give legal advice or certify compliance.
Do you fine-tune or quantize models?
No. I deploy and connect existing open models. I do not train or fine-tune them.
