Thank you.
#1
by
FiditeNemini
- opened
Thanks very much for the quants, much appreciated. I wasn't having much luck with llama.cpp, it kept failing to quantise, especially Q8_0, even though the f16 GGUF worked fine, just horribly slowly. Did you do anything special to get it to quantise properly? And thanks again for the quants, it saved me pulling out what's left of my hair... :)
Weird. No, it needed no attention at all, other than queuing it up and waiting. A well-mannered model :) Anyway, cheers!
mradermacher
changed discussion status to
closed