this post was submitted on 25 Dec 2023

1938 points (97.9% liked)

People Twitter

whitepeopletwitter@sh.itjust.works

10,399 readers

6,600 active

526 users here now

People tweeting stuff. We allow tweets from anyone.

RULES:

Mark NSFW content.
No doxxing people.
Must be a pic of the tweet or similar. No direct links to the tweet.
No international politcs
Be excellent to each other.
Provide an archived link to the tweet (or similar) being shown if it's a major celebrity, figure or any politician. You can replace the addres of .x.com to xcancel.com in the address. https://web.archive.org/save is an option. Archive.is is no longer recommended because they remove/alter content.
If a tweet (or similar) makes a statement of fact, either mark it as "satire" in the body or provide the original source link backing up the statement (see rule 6)

founded 3 years ago

moderators

SendMeYourTaTas@sh.itjust.works

pelespirit@sh.itjust.works

The dream (lemmy.world)

submitted 2 years ago by Stamets@lemmy.world to c/whitepeopletwitter@sh.itjust.works

237 comments fedilink hide all child comments

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

[–] CeeBee@lemmy.world 38 points 2 years ago (1 child)

It's getting there. In the next few years as hardware gets better and models get more efficient we'll be able to run these systems entirely locally.

I'm already doing it, but I have some higher end hardware.

parent

hideshow 2 child comments

[–] Xanaus@lemmy.ml 4 points 2 years ago (2 children)

Could you please share your process for us mortals ?

parent

hideshow 4 child comments

[–] CeeBee@lemmy.world 6 points 2 years ago

Stable diffusion SXDL Turbo model running in Automatic1111 for image generation.

Ollama with Ollama-webui for an LLM. I like the Solar:7b model. It's lightweight, fast, and gives really good results.

I have some beefy hardware that I run it on, but it's not necessary to have.

parent

[–] Ookami38@sh.itjust.works 2 points 2 years ago (1 child)

Depends on what AI you're looking for. I don't know of an LLM (a language model,think chatgpt) that works decently on personal hardware, but I also haven't really looked. For art generation though, look up automatic1111 installation instructions for stable diffusion. If you have a decent GPU (I was running it on a 1060 slowly til I upgraded) it's a simple enough process to get started, there's tons of info online about it, and it's all run on local hardware.

parent

hideshow 2 child comments

[–] CeeBee@lemmy.world 2 points 2 years ago (1 child)

I don't know of an LLM that works decently on personal hardware

Ollama with ollama-webui. Models like solar-10.7b and mistral-7b work nicely on local hardware. Solar 10.7b should work well on a card with 8GB of vram.

parent

hideshow 2 child comments

[–] ParetoOptimalDev@lemmy.today 1 point 2 years ago

If you have really low specs use the recently open sourced Microsoft Phi model.

parent