How Do I best host a highly tweakable and highly fine tunable self hosting model?

I have a GTX 1060 6gb graphics card and an i7 processor from 2012, I plan to upgrade eventually. I already have ollama with some models but I want to make them more sophisticated like chatgpt or deepseek or grok the best they can for my specs right now, I also want to access the locally hosted llm from my android phone over Wi-Fi so i am not sure if I need to use an API which I never used before, if I do what do you recommend?

1 Like

For now, Ollama itself works as a local server, so if you make it public within your home network, you should be able to use it via Wi-Fi.

You’ll need to consider what you’re going to do on the client side…