Quantization made by Richard Erkhov.

Github

Discord

Request more models

google-gemma-2b-dequantized - GGUF

• Model creator: https://huggingface.co/justinxzhao/
• Original model: https://huggingface.co/justinxzhao/google-gemma-2b-dequantized/

Name	Quant method	Size
google-gemma-2b-dequantized.Q2_K.gguf	Q2_K	1.08GB
google-gemma-2b-dequantized.IQ3_XS.gguf	IQ3_XS	1.16GB
google-gemma-2b-dequantized.IQ3_S.gguf	IQ3_S	1.2GB
google-gemma-2b-dequantized.Q3_K_S.gguf	Q3_K_S	1.2GB
google-gemma-2b-dequantized.IQ3_M.gguf	IQ3_M	1.22GB
google-gemma-2b-dequantized.Q3_K.gguf	Q3_K	1.29GB
google-gemma-2b-dequantized.Q3_K_M.gguf	Q3_K_M	1.29GB
google-gemma-2b-dequantized.Q3_K_L.gguf	Q3_K_L	1.36GB
google-gemma-2b-dequantized.IQ4_XS.gguf	IQ4_XS	1.4GB
google-gemma-2b-dequantized.Q4_0.gguf	Q4_0	1.44GB
google-gemma-2b-dequantized.IQ4_NL.gguf	IQ4_NL	1.45GB
google-gemma-2b-dequantized.Q4_K_S.gguf	Q4_K_S	1.45GB
google-gemma-2b-dequantized.Q4_K.gguf	Q4_K	1.52GB
google-gemma-2b-dequantized.Q4_K_M.gguf	Q4_K_M	1.52GB
google-gemma-2b-dequantized.Q4_1.gguf	Q4_1	1.56GB
google-gemma-2b-dequantized.Q5_0.gguf	Q5_0	1.68GB
google-gemma-2b-dequantized.Q5_K_S.gguf	Q5_K_S	1.68GB
google-gemma-2b-dequantized.Q5_K.gguf	Q5_K	1.71GB
google-gemma-2b-dequantized.Q5_K_M.gguf	Q5_K_M	1.71GB
google-gemma-2b-dequantized.Q5_1.gguf	Q5_1	1.79GB
google-gemma-2b-dequantized.Q6_K.gguf	Q6_K	1.92GB
google-gemma-2b-dequantized.Q8_0.gguf	Q8_0	2.49GB

Original model description: Entry not found