News for hackers. Stuff that matters.
Re:Mistral Releases Deep Research, Voice, Projects in Le Chat by randomNumber7 on Thursday July 17, 2025 @02:56PM (#44596792)
It is completely unreasonable to buy the hardware to run a local model and only use it 1% of the time. It will be unreasonable in 2026 and probably very long after that.

Maybe s.th. like a collective that buys the gpu's together and then uses them without leaking data can work.

Re:Mistral Releases Deep Research, Voice, Projects in Le Chat by ikt on Thursday July 17, 2025 @10:37PM (#44600644)
over time you would assume the models will get more efficient and the hardware will get better to the point that buying a massive new gpu with boatloads of vram is just not necessary

maybe 128gb of vram becomes the new mid tier model and most llms can fit into this nicely and do everything one wants in an llm

given how fast llms are progressing it wouldn’t surprise me if we reach this point by 2030