- cross-posted to:
- localllama@sh.itjust.works
- cross-posted to:
- localllama@sh.itjust.works
“A terminal tool that right-sizes LLM models to your system’s RAM, CPU, and GPU. Detects your hardware, scores each model across quality, speed, fit, and context dimensions, and tells you which ones will actually run well on your machine.”
You must log in or register to comment.
Its a nice utility, but I’m unsure how the “score” is evaluated. Probably outdated too, cause I have gemma3 q8 installed(for the sake of having one locally), and it didn’t detected it.
I don’t know about that username tho.
Yeah, I didn’t see the ‘s’ at first and imagined the code’s output screamed at you about gay frogs and wokeness if you selected certain LLMs.
Seems like a really good idea though, and I could definitely find this useful.
