A VM is practically as secure as a dedicated machine. I mean in theory it isn’t. But in practice, that’s how everybody does it, including the big tech companies. And there’s rarely any dangerous vulnerabilities.
It all depends on how you set it up. If the machines lack proper firewalling and can reach internal services. If you didn’t set some permissions right. Or there is a vulnerability in the software or the way it’s installed… I think that’d be the main concerns. And it doesn’t matter too much which exact virtualization or containerization setup you choose, as long as it provides isolation, and also isolation from the networks it isn’t supposed to access.
I think this warrants an extra post. And the beginners thread is a year old and I guess not a lot of people watch comments there.
I use KoboldCpp and like to recommend that to people who are new to the hobby or don’t own a proper gaming rig. It’s relatively easy to install and you can try it now, without any GPU, and see if you like it. I’d say it’s usable on CPU up to about 13B (with quantized models). Of course it’ll be orders of magnitude slower than a GPU.
I’d say every bit of VRAM counts. So you might as well buy as much as you can afford. And you’ll be able to run more intelligent models. Use one of the VRAM calculators to see what fits in 16GB or 24GB. And if you need that model and context size.