Well that escalated. I think racism, sexism, all the -isms really are a sign of stupidity, which everyone can be a victim of. Apart from very few people that are physically incapable of feeling empathy, everyone is capable of empathy. And a smarter person is significantly easier to reason with than a dumb person. I fully subscribe to the materialist idea here that not we shape our environment but our environment shapes us. And unfortunately, there is a lot of propaganda going around that tries to dehumanize others. It is easier to switch of the empathy part of your brain. The nazis were very good at this and pretty much the whole imperial core has copied their tactics. But then again psychopaths tend to gravitate towards positions of power.

Maybe i am naive and completely wrong about all of this though. If an idiot that fucks everything up as quickly as possible is actually the most optimal way to overcome the current system, then that’s it i guess. I don’t have a leg in the game after all. I am just an observer and try to not make things worse in my day to day life.

So yeah, maybe you are right. I really don’t want to argue about this. I want this to be over as quickly as possible, just like you.

i also said in another comment that i don’t think that the trajectroy would have changed with a more intelligent capitalist at the top. It is still capitalism after all. Self destructive system with falling profit rates and all. I definitely didn’t want to imply that i want it to maintain its power for longer.

yeah absolutely. The core can go to shit. I was rather talking about all the collaterals that have to suffer as the dying empire lashes out in desparation/confusion.

fair point. I think however that the trajectory the USA is on would not have changed significantly even with the Democrats in power and the world would have maybe avoided at least a few tragedies. Not the big one in Palestine, obviously. Everyone seems to be on board with that one. But i don’t know, to be honest with you. I just hope that that whole shit is over sooner rather than later …

I am not american. Don’t get me wrong, I fully agree that america losing it’s imperial power is absolutely a good thing. I am just saying that it is significantly more difficult to argue with a dumb person than with a smart(er) person. And a dumb person in power is just pure chaos. Idk at the end of the day it is useless to argue about what could have happened. History unfolds the way it does and we should try and make the best of it.

dump is always worse. It is chaotic, self destructive and pulls everything and everyone further down more quickly.

you know there are weight classes right?

the 27b model fits completely on the gpu so ram and cpu makes no difference.

For the deepseek model you need a fast ssd because no matter how big your ram is that model won’t fit there since it is almost 300gb.

I’ve got a ryzen9 5900x and 40gb ram. I don’t know how much of an impact the cpu actually has because i think most of it is evaluated on the gpu but could be that the router that selects the experts is executed on the cpu.

in any case the main impact will probably be vram size, pci-e throughput and ssd read speed (and maybe cpu speed).

qwen3.8-ridge-gguf runs great in ollama on the 9070xt in 4bit kv cache quant at 35t/s. You can also run deepseek 4.1 flash in strata if you have time. both models are very capable.

I have nothing really to compare it to in terms of the big ones because i refuse to give anthropic/openai any money. But i have used this qwen model in opencode to port an old CUDA/Optix based project to HIP and that worked fairly well. Not an overly complex refactor to be honest because 99% is just replacing the cuda prefix everywhere with hip, but it did fix the CMakeLists.txt for me and ported the optix prime acceleration structure to hipRT as well. I also let it vibecode a react based portfolio page because i have absolutely 0 knowledge of web development and refuse to learn it because i think it is insane and that turned out perfectly fine as well.

So it is absolutely usable for real world projects and the performance is quite OK as well with ~35tok/s. If i up the context size to the full 256k window, the performance drops to 5 tok/s, which is ok, if i let it do a boring refactor over night but at that point it isn’t faster than running DeepSeekV4.1-Flash-1017 through Strata and that one is much closer to the current SotA.

Definitely exciting times. We are close to being able to run very capable LLMs locally that are more than good enough for development. I am personally not a fan of 100% vibe coded projects anyway, because i like to architect things myself, so letting it go in smaller steps and/or help be with the boring stuff is absolutely fine. Unless the project is some personal stuff that just needs to solve one simple problem then vibe coding is fine imho.

I’ve been running the Ridge-GGUF version on my RX 9070 XT with ~60-80k contextsize with q4 kv cache quantization. Everything fits completely in 16GB VRAM

have been using a suri for half a year now. Awesome device. Doesn’t do anything useless like bluetooth or “smart” features. Just brushes teeth. And that perfectly well, while being super compact and with an enormous battery capacity.

And it is not ridiculously expensive either.

i bought a used sony a6700 with a sigma 18-50mm for that very reason. Not that pocketable but small enough and i actually shoot more because i usually keep it in my hand when i am travelling. An the creative styles + white balance bias means, i barely ever manually edit the raws and i can transfer them wirelessly to my phone and sync them automatically with my immich server.

I have anothet compact ttartisan 25mm f/2.0 as a fun/more compact lens for when i want it a little more pocketable.

Probably one of the best purchases i’ve ever made.