Thank you. Any experience?
#1
by
engrtipusultan
- opened
Thank you for doing GGUF. I have you tried it, does it work with llama.cpp?
Any recommended sampling settings?
Yes that's why I made them, to load them into llama.cpp.
I've just played around with it on the default settings so for and it seems to be happy,, but I didn't have the time to make something more analytical.
But as it's based on Qwen3-VL so you can try the same parameters.
noctrex
changed discussion status to
closed