LocalLLaMA

5654 readers

178 users here now

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

Rules:

Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.

Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.

Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.

Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.

founded 3 years ago

MODERATORS

pax@sh.itjust.works

noneabove1182@sh.itjust.works

Smokeydope@lemmy.world

MonsterBug@sh.itjust.works

554

Sam Altman: "Local inference is a terrible allocation of scarce resources" (twitee.co)

submitted 2 weeks ago by Shatur@discuss.tchncs.de to c/localllama@sh.itjust.works

158 comments fedilink hide all child comments

Sam Altman:

A lot of people want local inference, and somehow they assume that the problem is solved now because we have open-source models, we're going to be able to run them on our computers, and so we're not going to need all the stuff in the data center.

But from a global allocation perspective, actually it's quite terrible to have everybody, like, have a bunch of the world's limited supply of DRAM sitting in their own computer and being used five percent of the time.

Like you want maximum utilisation in the cloud if you're trying to deal with this very supply-constrained environment,

And somehow many people's intuition is the opposite of that

TL;DR Guy selling product: "Here's why owning your own product instead of renting it from me is a terrible idea"

you are viewing a single comment's thread
view the rest of the comments

[–] GeirGrusom@lemmy.world 3 points 2 weeks ago (1 children)

Yeah, they say on the spreadsheets that these cards have a lifetime of 5-6 years when in reality it's between 2 and 3.

[–] SupraMario@lemmy.world 4 points 2 weeks ago

5-6 is laughable for these guys... you're %100 correct. 5-6 years is for companies running their own stuff and even then, if you're hosting for clients that have any security measures in place, they will not be happy with you running aging and potentially EOL/S equipment.