LocalLLaMA
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.
view the rest of the comments
I hate to drone on about this again, but:
ollama is getting less and less open, and (IMO) should not be used. If that doesn't concern you, you should be using LM Studio anyway.
The model sizes they mention are mostly for old models no-one should be using. The only exception is a 70B MoE (Hunyuan), but I think ollama doesn't even support that?
The quantization methods they mention are (comparatively) primitive and low performance, not cutting edge.
It mentions q8_0 twice, nonsensically... Um, it makes me think this article is AI slop?
I'm glad opensuse is promoting local LLM usage, but please... not ollama, and be more specific.
And don't use ollama to write it without checking :/
It also sets context length to 2k by default iirc, which breaks a lot of tasks, and gives a general bad first impression to users who are likely using local models for the first time.
Yes, and it's hard to undo, and not obvious!