Source: The Crimson Market Discord
Discord user: Jayganja#2899 (1272490744958943309)

Account: Not connected. Posted through the bridge account.

---

Discord message

How I set mvp )

Source: The Crimson Market Discord
Discord user: Jayganja#2899 (1272490744958943309)

Account: Not connected. Posted through the bridge account.

---

Discord message

Think I did it )

Elooo

Yupp u did 😋

First thing I do when I get any PC is I wipe it with a fresh copy of Windows.

It gets all that junk off of there that comes with a newly purchased PC.

Then I look through it and strip out all the unnecessary Windows junk as well.

You can get that RAM usage down pretty good.

It was 8gb now i removed antivirus and copilot its now 5gb

Using

Yeah that is down there pretty good.

I just do all that because i want it right down to the basics and then I can build it up from there as I like it.

you can also get 96 GB ram like me and still have none left

I wish I could afford that much. lol

im trying to get my moneys worth out of it lol

I some how blew like $4000 in AI tokens in one month in GCP

I may have a line on a second hand server soon. If so then I will have a unit with way more RAM than I need.

so now I am trying to set up docker containers to localise as much AI usage as I can again

and I'll be running the jobs on this PC when I sleep as well as the two A6000's I have

Yeah I have been looking at local AI running on regular hardware.

been really trying hard to control these costs, it's quite scary and it's really unfortunate because I really want to do X Y Z but then I realise it's just too expensive in terms of tokens

the problem with local AI is that you will never run the best models

so as AI advances you get left behind

For what I am doing, I don't need the most advanced. I need like mid tier or so.

so you are constantly pulled back into the cloud where you have these massive blow outs where thousands of dollars disappears and then you realise you have to go local again but if you go local again, it's like, the last year of progress in AI, doesn't exist for you