Calls it "Deepsneak", failing to make it clear that the reason people love Deepseek is that you can download and it run it securely on any of your own private devices or servers - unlike most of the competing SOTA AIs.

I can't speak for Proton, but the last couple weeks are showing some very clear biases coming out.

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

[–] halcyoncmdr@lemmy.world 25 points 12 hours ago (2 children)

There are plenty of step-by-step guides to run Deepseek locally. Hell, someone even had it running on a Raspberry Pi. It seems to be much more efficient than other current alternatives.

That's about as openly available to self host as you can get without a 1-button installer.

[–] tekato@lemmy.world 12 points 12 hours ago (2 children)

You can run an imitation of the DeepSeek R1 model, but not the actual one unless you literally buy a dozen of whatever NVIDIA’s top GPU is at the moment.

[–] lily33@lemm.ee 8 points 10 hours ago

A server grade CPU with a lot of RAM and memory bandwidth would work reasonable well, and cost "only" ~$10k rather than 100k+...

[–] alcoholicorn@lemmy.ml 0 points 7 hours ago

I saw posts about people running it well enough for testing purposes on an NVMe.

[–] Dyf_Tfh@lemmy.sdf.org 4 points 12 hours ago* (last edited 12 hours ago) (1 children)

Those are not deepseek R1. They are unrelated models like llama3 from Meta or Qwen from Alibaba "distilled" by deepseek.

This is a common method to smarten a smaller model from a larger one.

Ollama should have never labelled them deepseek:8B/32B. Way too many people misunderstood that.

[–] yogthos@lemmy.ml 2 points 10 hours ago (1 children)

I'm running deepseek-r1:14b-qwen-distill-fp16 locally and it produces really good results I find. Like yeah it's a reduced version of the online one, but it's still far better than anything else I've tried running locally.

[–] morrowind@lemmy.ml 1 points 2 hours ago

Have you compared it with the regular qwen? It was sissy very good