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:
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.
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.
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>.
No implying that models are devoid of purpose or potential for enriching peoples lives.
view the rest of the comments
Ive tried DeepSeek, it’s not even that good. ChatGPT, Google, and even Grok are better and offer more features, like image generation and web search, while DeepSeek only has chat (and reasoning, but all the others have that too now).
The only thing DeepSeek has going for it is that they released their models for free so you can run them on your own hardware if you want.
that's a big fucking benefit though
You mean being able to run them locally? Sure, if you got the hardware to do it. The full size model is a whopping 404 GB, good luck running that on consumer hardware.
I run the 16b version. It works fine on my laptop on the CPU.
Sure, that’ll work. It’s just not as smart as the full version.
Deepseek is much better than anything else I've ran. It has an inner monolog which allows it to solve more complex problems.
ChatGPT and Grok have that too now. It’s called “Reason” (ChatGPT) or “Think” (Grok).
You can't run those locally though so that doesn't natter much
I guess I forgot what community I'm in 🤦♂️
All good