The insane AI push is purely driven by fear of being left behind.
No one is actually stopping to ask whether it is all worth it.
The insane AI push is purely driven by fear of being left behind.
No one is actually stopping to ask whether it is all worth it.
Can any of this be run on say a 9070XT or 5070TI?
github.com/ggml-org/llama.cpp
ya I run Llama, good shit.