Run Local ChatGPT & AI Models on Linux with Ollama 

Good stuff family! I’m going to try this out!

This makes me hopeful for the future of computing. Being able to host these services locally is fantastic.

Thanks for the content! Great and clear instructions. I was able to get it up and running with my 4060 great. Keep the great vids coming!

Muchas Gracias Josh! your video was very helpful for me. Thanks!

Josh, I followed up on my comment to your twitter post for this video. I got ollama containerized and have added the breezy golang UI to it. I still need to setup docker GPU passthru in order to speed it up. The tokens come real slow right now. LOL My next step is to train it with my own data. This video is good stuff bro, thanks.

Very Cool! Thank You! I added a Tesla p4 card and passed it through in proxmox to a debian VM. works very well!

How much can you train a model?

Just installed it. Thanks bro!

THanks! This is very useful. I’m going to try this out.

great stuff. bro,

Can you run any of these models on a Live Kali Linux USB bootable thumb-drive ?

if anyone is having issues connecting to your webui, make sure you have port 8080 open on your linux machine

Good content bro 😎

How to get model offline , I don’t have internet connection to my Linux , is there anyway to get any model like llama2 manually using a zip offline ?

if i ignore the speed / slow issues, can we run any model on any hardware

Thank God for that, I finaly got one to work out of the box sucessfully

Shout out too you Keep it tech all well?

Keepittechie. 🫡! THAGOD°♤°GOLD•P

It’s not local 😂

Too complicated😂

No wonder newbies leave Linux it's too complicated