https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-7B-GGUF/tree/main
Discussion
I'm confused. What is deep seek? Tech retard here.🙏
open source large language model
So AI?
yes, like chat gpt, but you can run it on your own machine
Umbrel or start9 then?
you need a powerful GPU to run these models. Usually something like a gaming PC has one. I thin new apple chips can also run them, but I don't know much about that.
I'm running local models like the one above on an nvidia 4070, and the fan goes spinning pretty hard
I lost you at powerful GPU.🤣 I don't have any of that hardware. Not kidding, completely retarded when it comes to tech. 🤷
sorry 😅
GPU means graphical processing unit, it's a special type of computer chip that is specialized for parallelizing workload, which works well for AI stuff.
Let's hope this stuff becomes easier to run locally, so we don't have to use the evil Corp models 💛
Dm'd cuz I have some questions about doing this myself!
good for coding?
Funny that your note and this note appeared very closely on my timeline 😂
Open source self hostable models by small teams are destroying million dollar funded closed source models. There is hope if you look for it in the right places.
Sounds promising...
Brian Roemmele:
"If overnight tests are confirmed we have OPEN SOURCE DeepSeek R1 running at 200 tokens per second on a NON-INTERNET connected Raspberry Pi.
A full frontier AI better than “OpenAI” owned fully by you in your pocket free to use!
I will make the Pi image available as soon as all tests are complete.
You just pop it into a Raspberry Pi and you have AI!
This is just the start of the power that takes place when you TRULY Open Source an AI Model."
What is the difference between this model and the original DeepSeek-R1?
It's unfortunately still pretty slow on my phone...
I guess that's an unreasonable complaint though