Well, to be fair, the US started a really bloody war of aggression against another country with full ground invasion, based on entirely made up justifications already in 2003. Not sure how it was in wars prior to that though.
Jiral
joined 4 months ago
Please educate us. What international law was violated by attacking military and logistics facilities that support the aggressor army, on its home turf?
More competition is better than less. It is that simple. Your argument is just either nihilistic or an excuse to support a duopoly.
European data is an option too.
At least it is US Americans paying that tariff bill.
Ah, so that is why these AfD guys are in their Russian motherland again.
I fully understand. ;) Buying hardware now means you'd be either crazy or desperate.
Yes I think Strix Halo makes sense when low power use is a requirement. I built a custom fanless Strix Halo system for the fun of it and I guess there aren't too many out there running Gemma 4 31B Q8 without a single fan, anywhere.
And for MoE models that need 60-80GB + context it is perfect. Those are decently fast then as well.
PS: If VRAM is all you care about the maxed out Mac Studio is fascinating. 512GB unified memory for around 10K EUR (pre crazy bubble prices) That should be able to run pretty large MoE models but dense models of that size would probably run glacially.
That fails the point. Wero is good because it breaks open a duopoly and mitigates the risk that the US can bring the European economy to a halt via Visa/Mastercard.
More comoetition is good, monopolies aren't. Nor would a Wero monopoly be.
From a strategic view Wero is extremely important for Europe. You are looking from a cery different view on the topic but that does not invalidate that other view per se.
My own views are that we need a balance of control and chaos. Both extremes have substantual downsides.
My system runs at 100W TDP though. That is maybe 140W at the power outlet, incl. monitor and everything.
This is also the dense 27B model at Q8. But yeah, it is not terribly fast. I think the best use case is on MoE models. GPT-OSS-120B runs on it for example and at 50T/s speed is not a n issue anymore either. (I could get it to run even on just 64GB but the new llama.cpp might need a tiny bit more memory which pushed it just across the limit. yeah I know, for seriously using it you'd need the 128GB version)
view more: next ›
That would only be a problem if there were still rule of law in the US. If that were the case, they wouldn't be able to run all those gas turbines either.