# For Base Model

[theunknownmuncher@lemmy.world]

this is deepseek-v3. deepseek-r1 is the model that got all the media hype: https://huggingface.co/deepseek-ai/DeepSeek-R1

[thefartographer@lemm.ee]

r1 is lightweight and optimized for local environments on a home PC. It's supposed to be pretty good at programming and logic and kinda awkward at conversation.

v3 is powerful and meant to run on cloud servers. It's supposed to make for some pretty convincing conversations.

[cyd@lemmy.world]

Base models are general purpose language models, mainly useful for AI researchers and people who want to build on top of them.

Instruct models are chatbots. They are made by fine-tuning base models.

[jomusic@lemmy.ml]

Is that website legit?
I've only ever seen https://www.deepseek.com/

And I would personally recommend downloading from HuggingFace or Ollama

[pennomi@lemmy.world]

R1 isn’t really runnable with a home rig. You might be able to run a distilled version of the model though!

[theunknownmuncher@lemmy.world]

Tell that to my home rig currently running the 671b model...

[pennomi@lemmy.world]

That likely is one of the distilled versions I’m talking about. R1 is 720 GB, and wouldn’t even fit into memory on a normal computer. Heck, even the 1.58-bit quant is 131GB, which is outside the range of a normal desktop PC.

But I’m sure you know what version you’re running better than I do, so I’m not going to bother guessing.

[theunknownmuncher@lemmy.world]

It's not

[thefartographer@lemm.ee]

You're absolutely right, I wasn't trying to get that in-depth, which is why I said "lightweight and optimized," instead of "when using a distilled version" because that raises more questions than it answers. But I probably overgeneralized by making it a blanket statement like that.

[pennomi@lemmy.world]

You must have a lot of memory, sounds like a lot of fun!

[dogwater@lemmy.world]

I heard people saying they could run the r1 32B model on moderate gaming hardware albeit slowly

[fmstrat@lemmy.nowsci.com]

Yea, comment OP needs to edit links with howany up votes that got.

[frederiknjs@lemm.ee]

32b is still distilled. The full one is 671b.

[meliante@lemmy.world]

My legion slim 5 14" can run it not too bad.

[dogwater@lemmy.world]

I know, but the fall off in performance isn't supposed to be severe

[frederiknjs@lemm.ee]

You are correct. And yes that is kinda the whole point of the distilled models.

[dogwater@lemmy.world]

I know. Lmao