Comment on Selfhosted & AI
curbstickle@anarchist.nexus 2 days agoI’m just going to shortcut this and say two things:
I can guarantee the overwhelming majority (if not all) of your issues have nothing to actually do with LLMs and everything to do with corporations. Power use, data center buildouts, market impact, whatever - none it is an an llm problem. LLMs are just another piece of software, thats all.
Your personal opinion on this, as well as mine, does not change the overall conversation here. So how about we just stick to the topic at hand?
midribbon_action@lemmy.blahaj.zone 23 hours ago
LLMs are inextricably tied to nvidia gpus. Local or cloud, the technology exists to help the shovel salespeople. The gold diggers, everyone this tag is supposed to segregate, have been misled by corporations. Without their lies, and a pliant media, this tag would be unnecessary, and llms would be rolled out in a more limited and responsible way. To promote different uses of gold during a gold rush is going to inflate the bubble and enrich the rich, unless it is properly contextualized. Technology does not exist in a void, pretending it does digs us a deeper hole.
curbstickle@anarchist.nexus 22 hours ago
I run my local models on a Mac mini m2, but I could also be using AMD (ROCm), Intel with OpenVINO, or just CPU. Simple edge applications I could even use something like an RK3588.
Being tied to NVidia is marketing from NVidia, not the reality of LLMs.
midribbon_action@lemmy.blahaj.zone 22 hours ago
Congrats, you are in the 1%. And that is exactly the type of additional context I think is necessary when discussing it.
curbstickle@anarchist.nexus 21 hours ago
Sorry, I’m not following here. Are you suggesting I’m in the 1% of income earners? Because if so… LOL not even close, I’m barely in the top 40% by rough math.
Just to note, an apple silicon Mac is one of the most efficient (dollars, wattage, whatever take your pic) ways to run an LLM. Mine was a build target for iOS stuff for a client I’m now repurposing, that was a refurb that cost about $600.
I can’t even buy a GPU for that price these days.