[emsign]

Running models at home seems like a waste of money while at the same time they are currently heavily subsidized in the cloud by dumb money.

[borisk]

How is it a waste of money if a lot of people, including the author of the article, already have an nVidia GPU in their PC?

Running locally has a lot of advantages - privacy, getting to learn how to run LLMs, not having to deal with quotas, logins, outages.

[hu3]

Home electricity bill of a decent GPU alone is usually more expensive than renting GPUs on demand.

[borisk]

Do you have any numbers to back that statement up?

E.g. I have solar panels and a home battery and pay less than a $100 a year for electricity.

[hu3]

Solar panels aren't free. And aren't hassle-free either.

I wouldn't even bring that into the equasion since a large part of the population can't use solar panels.

Not to mention GPU value depreciation.

[chpatrick]

I use ChatGPT for most practical stuff but I really enjoy running local models. I find it really interesting and I think it's important for people to know how to run these without being beholden to big tech. If you have a used 3090 you can already run some really strong models. There are some really interesting local models as well, like the abliterated ones.

[sterlind]

it's nice to be able to have private conversations.

[calaphos]

There's also big efficiency increases when batching multiple requests, making clouds inherently more cost effective for normal use cases.

Way better utilization of expensive hardware as well ofc.

[cma]

Heavily subsidized on heavily price discriminated hardware (nvidia datacenter licensed hardware) kind of cancels out.

[hnfong]

Sometimes you don't want your workflow to be subject to the whims of some LLM API provider.