operablepattern/gemma-2b-it-Q

This repository contains gemma 2B models quantized using llama.cpp.

For details of the model see https://huggingface.co/google/gemma-2b-it.

Details of the k-quants can be found here: https://github.com/ggerganov/llama.cpp/pull/1684

Provided files

Name	Quant method	Bits	Size
gemma-2b-it-Q4_K_M.gguf	Q4_K_M	4	1.63 GB
gemma-2b-it-Q5_K_M.gguf	Q5_K_M	5	1.84 GB