CCATresearch/Gemma-2-2B_wllama_gguf
055
Gemma 2 2B quantized for wllama (under 2gb).
q4048 is WAY faster when using llama.cpp, with wllama, it's about the same as q4k.
Gemma 2 2B quantized for wllama (under 2gb).
q4048 is WAY faster when using llama.cpp, with wllama, it's about the same as q4k.