Please make Q8 gguf
#2
by
AImhotep
- opened
I can see 4bit and 16bit :)
make q1 smal
Sadly there's no llama.cpp support yet. Check this issue for more info: https://github.com/ggml-org/llama.cpp/issues/15940
I can see 4bit and 16bit :)
make q1 smal
Sadly there's no llama.cpp support yet. Check this issue for more info: https://github.com/ggml-org/llama.cpp/issues/15940