What i want:

Click login button

Cryptographic exchange happens

Done

I host my email on a hetzner VPS using dovecot+postfix and thus far no issues.

I don’t really understand why people are so against it, for me it took an evening to set up and haven’t touched its configuration since.

Now that you are posting this on the fediverse community.

Posted on Normals.me · View the original post

If your goal is not spamming then this is not needed.

The instance is already visible, and we are already viewing the original post as this is not a crosspost, and the federation button already provides a way for people to view the post as your instance serves it.

I host a matrix tuwunel server and can recommend it.

My motivations are that it gives greater control, and i think federated platforms are better.

I have it set up on a hetzner vps running debian, which tuwunel provides an official package for.

I would suggest trying exllamav3 once, i have no idea what kind of black magic they use but its very memory efficient.

i can’t load Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 with 16K using vllm

but using exlamav3 i can SOMEHOW load ArtusDev/Qwen_Qwen3-Coder-30B-A3B-Instruct-EXL3:8.0bpw_H8 at its full context of 262.144 with still 2GiB to spare.

I really feel like this is too good to be true and im doing something wrong but it just works so i don’t know.

If I were to guess the biggest peformance impact is if your driver doesn’t support newer types like FP4 and FP8 while your hardware does, but I am not sure.

Forget that the real evil is that the first character of Int or Ganz in this case is capitalized

Haven’t used shotcut or openshot but can recommend kdenlive, it has alot of features but I find it a bit clunky sometimes to work with.

For me when I was working on a large project it crashed once and the autorecover worked, although I still manually save since I’m paranoid.

I’m selfhosting Forgejo and i don’t really see the benefit of migrating to a container, i can easily install and update it via the package manager so what benefit does containerization give?

Well that’s annoying

My banking app worked with waydroid on linux

I genuinely hope something else comes along soon. And no I don’t want Apple, they’re even worse than Google.

There are a few usable linux phones you can look into, but they do come with drawbacks.

I honestly prefer MK8 over world, the long straight “tracks” are really boring.

Ah yes because there is no other possible way to combat organized religion then executions. /s

I am really curious how the T/s scales with network speed, as said in the video 5G is quite slow.

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.

Thanks! Ill go check it out.

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.