Yeh, I’m down the LLM rabbit hole lately, but check this out. You can now run LLAMA in a low-end Digital Ocean droplet.

https://github.com/ggerganov/llama.cpp/discussions/638

Reply to this note

Please Login to reply.

Discussion

Same, still getting a handle on what they can do, with LoRAs and all. It's tough to keep up with everything.

Now I have to try this 30B llama model šŸ˜…

Sounds like Silicon Valley

Pied Piper

Oracle Cloud used to give you 4xA100 High Performance ARM processes with 24gb of Ram for free might be worth a look.

I use them for running BTC Pay server but this might be a better use :)