Browse categories
Explore
Fiverr Pro
English
$
USD
I will set up a private self hosted llm on your own server with your data
Yang Ye
About this gig
Your data cannot leave the company? I set up private AI on your own server: open-source LLMs running on your GPU, with an API compatible with OpenAI so your apps can use it.
I run this in production: a company AI platform on an in-house NVIDIA GPU server, with chat, agents, RAG over documents and email, and scheduled reports. No data goes to the cloud.
What I set up:
- Model choice and sizing for your hardware (or advice on what GPU to buy)
- Inference server (Ollama / vLLM) with an OpenAI-compatible API
- Private web chat for your team, with users
- Optional: RAG over your documents and connection to your apps
- Monitoring, updates and handover documentation
Works on Linux or Windows servers, on-premise or in a private cloud.
Get to know Yang Ye
Yang Ye
Full Stack and AI Developer, Angular, NodeJS, LLM, RAG, CRM, ERP
- FromSpain
- Member sinceApr 2023
- Last delivery2 years
Languages
English, Chinese, Spanish, Catalan
Full-stack developer and industrial engineer (MEng). I lead the technology of a software company and build custom business software: CRM/ERP platforms, quoting engines, e-invoicing and dashboards with Angular, Node.js and MySQL. I specialise in putting real AI inside business apps: LLM assistants that act on your data, RAG over documents and email, AI document extraction and private self-hosted models on GPU servers. 8+ years of experience. I speak English, Spanish, Catalan and Chinese.
My Portfolio
Other AI Development Services I Offer
FAQ
What hardware do I need?
It depends on the model and the number of users. Send me your server specs and I will recommend a model; I can also advise on buying a GPU.
Is it as good as ChatGPT?
Modern open-source models are very good for most business tasks. I will test your real use cases before you decide.
Do you need remote access?
Yes, SSH or remote desktop to the server during the setup.
