LocalLLaMA

localllama@sh.itjust.works

5,457 readers

2,442 active

442 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

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

submitted 9 hours ago by Shatur@discuss.tchncs.de to c/localllama@sh.itjust.works

41 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

[–] AmbitiousProcess@piefed.social 13 points 7 hours ago

As if the ONLY thing your memory could be used for is running AI models.

Hey buddy, we need this shit to use our BROWSERS or to play GAMES. I have a GPU in my computer that can run most new AI models when quantized at a speed that would be perfectly reasonable for any home user that doesn't want it to literally replace every ounce of their thinking, and I bought that shit before ChatGPT was even a thing, because I wanted to play fucking video games.

I have a NAS with 16 gigs of RAM and a consumer-grade CPU that's a few generations old, and it can still run models with zero GPU or AI accelerator if you give it a little time.

Is it going to be perfectly tuned, and run at the highest possible speed if you design a datacenter just for AI models? Of course it is. But do most people on this planet need that or give a fuck about it? Absolutely not.

permalink

fedilink

source