theyre scared of doing their own art because they risk being ridiculed for mediocre tehnique. they vent to chatgpt because theyre afraid of being rejected in early friendships and just want someone to say they love them. they dont go to therapy because 9 dollars a month is way cheaper than 800 dollars. they use AI chatbots for sex because theyre afraid of the very real risks of sex and dont feel like they can get it with a real person. we used to vent online but now post pandemic you risk your shit being posted on a commentary channel blasted to millions of people in your most vulnerable times.
dog i use it to speed up searching for stuff and doing translation locally. i dont spend money on it.
if youre on this app and subscribe to a socialist worldview then i hope you can understand that when you use something for free you are the product (unless you use a socialist AI model)
i run chinese models locally. there is no way for them to make money off me. i even run my own searxng mcp-server instance with tor added. theres zero way for anything to be tracked or profited from.
I’m curious what model you run and on what hardware?
qwen 3.6 35b a3b, 2k usd custom build computer from 2-3 years ago with about 80gb cumulative vram/ram that was partially paid for by my employer. i do nondescript science™️ for my job. its pretty useful for dredging the internet for sources, especially sources that would be normally inaccessible to me because i dont speak the language the paper is in. my previous computer was falling to bits (nearly 20 years old, i hope i can make this one go that far) so i needed a good one anyways. its also good at looking over code for obvious bugs, and somewhat decent at coding functions (important: FUNCTIONS) not whole projects.
Nice, I recently got this thing running on an igpu at 20 tok/sec token generation, it’s surprisingly capable. Seems to be the best MoE model of it’s size. I’ll soon be getting a gpu server (dual rtx 5060ti 16gig), so I’m excited to see how fast it can go
its an extremely capable model at this size. i think most of the effort must be spent on miniaturizing models, as the smaller they get the more useful they become to the widest number of people
How on earth do you have 80 gigs of VRAM?
this model can be compressed to as low as 12 gigs (though I wouldn’t recommend going that low due to a huge quality drop). And not all of this kind of model has to reside in vram - you can have most of it in ram and the rest gets cached in vram
I’m curious, can the model fill your whole VRAM or do you have to leave extra space for the actual, you know, whatever it’s doing? Like, could you actually do anything with the 12gb model if you only have 12 GB of VRAM?
Yes, you need to leave some space for the context (kv cache) - a lot of space if you need a lot of context. Large context just allows you to generate more text and run longer tasks.
12 gigs is actually a good amount to run this class of model. As I said, not all of the model has to live in the vram
here is an example of a guy running a 35 billion parameter model on gtx 1060 (6 gigs of vram) at 36 tokens a second with max context size, a good speed for most tasks. Point is, these days you can run fairly capable models on ancient hardware if you know what you’re doing
cumulative, i only have ~16gb vram. models run slower on normal ram but with some tweaks and a somewhat decent gpu you can make them run around 30-40 tokens/s which isnt exactly fast for complex tasks, but is still very useful if you’re willing to wait.
Oh, I see. So, I have 44gb cumulative ram, 12gb VRAM and 32gb “regular”.
I was hoping there was some magical way to improve my 4070ti (not super).
china isnt socialist cause they make llms
Oh that’s not what I’m saying at all. I fully suppot the Alibaba Corporation and their socialist stochastic text generators
https://www.businessinsider.com/xi-jinping-china-ai-wins-new-year-address-2026-1?op=1
edit better source
https://english.www.gov.cn/news/202607/17/content_WS6a5a1172c6d00ca5f9a0c46b.html
Do you realize that socialists aren’t obligated to be in favor of something just because Xi is?
he was saying ai models cannot be made in a socialist way. the leader of the largest communist party on earth endorses their open development for the automation of the economy. these two statements are incongruent if you think china is doing things correctly.
And despite how often people are brow-beaten for saying so on this website, not everyone thinks China is doing everything correctly.
LLMs are intrinsically bad because they degrade people’s brains and frankly I personally think the automation of thought simply is not something that is in line with human flourishing, that doesn’t change if such things are apparently happening Socialistly.