different Q4 models
#1
by
animax
- opened
Thank you for the great work. Could I know what the different in these models?
SuperNova-Medius-Q4_0_4_4.gguf
SuperNova-Medius-Q4_0_4_8.gguf
SuperNova-Medius-Q4_0_8_8.gguf
They are the same size.
Those are special GGUFs for ARM processors (Not for Apple Metal GPU Offloading). 😋
https://github.com/ggerganov/llama.cpp/pull/5780#pullrequestreview-21657544660