A lot, but less than you’d think! Basically a RTX 3090/threadripper system with a lot of RAM (192GB?)

With this framework, specifically: https://github.com/ikawrakow/ik_llama.cpp?tab=readme-ov-file

The “dense” part of the model can stay on the GPU while the experts can be offloaded to the CPU, and the whole thing can be quantized to ~3 bits average, instead of 8 bits like the full model.

That’s just a hack for personal use, though. The intended way to run it is on a couple of H100 boxes, and to serve it to many, many, many users at once. LLMs run more efficiently when they serve in parallel. Eg generating tokens for 4 users isn’t much slower than generating them for 2, and Deepseek explicitly architected it to be really fast at scale. It is “lightweight” in a sense.

…But if you have a “sane” system, it’s indeed a bit large. The best I can run on my 24GB vram system are 32B - 49B dense models (like Qwen 3 or nemotron), or 70B mixture of experts (like the new Hunyuan 70B).

I've never heard of "Grok".

Its Musk's LLM, which interacts with people on X. He's been paying people to tune it to be more hate-oriented for years.

Where do you think the Nazis got the salutes from? And for that matter, where do you think we got the word fascism from?

If I perform a certain gesture, does that make me a fascist?

So Italians turn out to be bad, hmm, but you're not a Nazi, I've understood correctly, right?

If you make Roman/Nazi salute than your opinion is not worth considering. Either you're doing it because you approve of an ideology that will always fail, or you lack the contextual awareness to form an insightful opinion.

Edit: judging from your comment history, if you posted an image for yourself doing the salute I would say the latter. But we all know you're too ashamed/scared to share an image of yourself doing that "gesture"

Nazi trains a nazi "speak & spell"

Whoopty fucking do.

The problem comes when large portions of the population use it and accept what it says without any shred of critical thinking.

Took 'em long enough to get around to this result, I'm shocked that the boy genius would let it operate in "bash me because that's what the majority of the world thinks" mode for so long.

I'm beginning to think those people are already lost... anyone who is going to fall for this has already fallen for similar things and reflexively distrusts anything that doesn't back up their world views.

I also think people who are opposed to this are very unlikely to change their minds based on something controlled by someone like that.

Finally, we've been at this hard for almost a decade, I'm pretty sure the undecideds are lying to the pollsters.

Last time I checked, Grok was still 'woke' (meaning: repeating the most common opinions published around the internet) - that's been a couple of months. I was shocked that it was permitted to be accessed by the public back then.

I don't think the system has that much sophistication.

I do think they can "weight" the training set and feed it endless variations of "approved content" to be regarded as correct, and maybe also feed it other content to be identified as "incorrect" and rebutted from the approved content.

You aren't playing dumb when people know you're playing.

So, basically, it is more like "normal" Twitter posts since then?

We won't.

I'm still surprised Heinleins family hasn't sued of nothing else but because Mike would not enjoy musk at all.

Then look it up?

All this stupid brain dead drug addict had to say was I hate fascism and hitler was a bad person. He did not. IMO case closed.

Why? This is giving it more attention than it deserves.

So you do know what it is then?