Self hosted LLM - sh.itjust.works

Hello internet users. I have tried gpt4all and like it, but it is very slow on my laptop. I was wondering if anyone here knows of any solutions I could run on my server (debian 12, amd cpu, intel a380 gpu) through a web interface. Has anyone found any good way to do this?

I use KoboldCPP, works perfectly over the internet. Not sure how Intel support is though, and with 6GB VRAM the whole thing is of questionable utility.