If there is a way to combine this with something like anubis this could be very interesting, then you are also not dependent on the honesty of reading the robots.txt
Have a RSL license? here you go scrape the content.
Ofcourse we would all rather see it using EU chips but the hard reality is that they don't exist.
So the tradeoff becomes can this thing produce more value for the EU using NVIDIA chips now instead of using EU chips someday on a hypothetical future date?
How is this not a “won’t somebody please think of the children” thing?
Yes it is terrible this has happend, but there is a way to prevent children from accessing AI and its called parenting.
Kids shouldn't be using AI if it harms them, kids can't make this choice so it should be made for them. Same with alcohol, same with porn, same with the other things restricted to children.
But that doesn't mean responsible adults shouldn't be able to use it, but “won’t somebody please think of the children” litigation will make that impossible.
I don't care if openai lose all their money but this ruling would also effect open source AI.
If somebody releases a AI why would they be liable for how people decide to use it? Its software and like any other program its the user's choice on how to use it.
If i decide to run rm / --no-preserve-root is gnu then responsible to fix it?
AI is already very censored, and if makers become liable for what people do with their AI they will become hyper censored and performance will go down the drain.
Let’s face it, the EU is too weak and reliant to achieve strategic autonomy at the moment.
Many people say this but it doesn't really made sense to me, if Russia can't even win against Ukraine how would they ever fight against the EU, our army is both larger and much better equipped then Ukraine.
And it doesn't look like there is a ceasfire going to be soon so Ukraine will keep fighting which means Russia doesn't even have the troops outside Ukraine to invade the EU, and if they somehow did then we would reach Moscow by next month.
Why do core counts and memory type matter when the table includes memory bandwith and tflop16?
The H200 has HBM and alot of tensor cores which is reflected in its high stats in the table and the amd gpus don't have cuda cores.
I know a major deterioration is to be expected but how major? Even in extreme cases with only 10% efficiency of the total power then its still competitive against the H200 since you can get way more for the price, even if you can only use 10% of that.
My target model is Qwen/Qwen3-235B-A22B-FP8.
Ideally its maxium context lenght of 131K but i'm willing to compromise.
I find it hard to give an concrete t/s awnser, let's put it around 50.
At max load probably around 8 concurrent users, but these situations will be rare enough that oprimizing for single user is probably more worth it.
My current setup is already:
Xeon w7-3465X
128gb DDR5
2x 4090
It gets nice enough peformance loading 32B models completely in vram, but i am skeptical that a simillar system can run a 671B at higher speeds then a snails space, i currently run vLLM because it has higher peformance with tensor parrelism then lama.cpp but i shall check out ik_lama.cpp.
While I would still say it's excessive to respond with "😑" i was too quick in waving these issues away.
Another commenter explained that residential power physically does not suppply enough to match high end gpus is why even for selfhosters they could be worth it.
Thanks, While I still would like to know thr peformance scaling of a cheap cluster this does awnser the question, pay way more for high end cards like the H200 for greater efficiency, or pay less and have to deal with these issues.
That is not far from the truth