LocalLLaMA

localllama@sh.itjust.works

5,616 readers

3,205 active

142 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

moderation log

moderators

MonsterBug@sh.itjust.works

Smokeydope@lemmy.world

pax@sh.itjust.works

noneabove1182@sh.itjust.works

"The cost of running LLMs is just too damn high" (aussie.zone)

submitted 5 months ago by SuspiciousCarrot78@aussie.zone to c/localllama@sh.itjust.works

6 comments fedilink hide all child comments

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

[–] Luminous5481@anarchist.nexus 7 points 5 months ago

I've been running Qwen3.6 35B very easily. but that's because I've got a ASUS Z13, which is one of the newish laptops that have the AMD Ryzen AI MAX+ 395 in it. you can get that chip with 128gb of unified memory, 96gb of which I have dedicated to be VRAM. I can also run Qwen3 Coder Next 80B. I'm not sure how many tokens per second I'm getting with Coder, but it's fast.

honestly I think this unified memory might be the future of mobile chips, because the things I can do with it are pretty crazy. it's not just useful for AI either, it's in a few gaming laptops because it also works really well when gaming. but the things you can do with LLMs or diffusion models is amazing. I donate compute to AI Horde, and I'm finishing image generation jobs for people in like 4 seconds.

permalink

fedilink

source