RichardErkhov/google_-_gemma-7b-gguf

GGUF quantization made by Richard Erkhov.

Github

Discord

Request more models

gemma-7b - GGUF

• Model creator: https://huggingface.co/google/
• Original model: https://huggingface.co/google/gemma-7b/

Name	Quant method	Size
gemma-7b.Q2_K.gguf	Q2_K	3.24GB
gemma-7b.IQ3_XS.gguf	IQ3_XS	3.54GB
gemma-7b.IQ3_S.gguf	IQ3_S	3.71GB
gemma-7b.Q3_K_S.gguf	Q3_K_S	3.71GB
gemma-7b.IQ3_M.gguf	IQ3_M	3.82GB
gemma-7b.Q3_K.gguf	Q3_K	4.07GB
gemma-7b.Q3_K_M.gguf	Q3_K_M	4.07GB
gemma-7b.Q3_K_L.gguf	Q3_K_L	4.39GB
gemma-7b.IQ4_XS.gguf	IQ4_XS	4.48GB
gemma-7b.Q4_0.gguf	Q4_0	4.67GB
gemma-7b.IQ4_NL.gguf	IQ4_NL	4.69GB
gemma-7b.Q4_K_S.gguf	Q4_K_S	4.7GB
gemma-7b.Q4_K.gguf	Q4_K	4.96GB
gemma-7b.Q4_K_M.gguf	Q4_K_M	4.96GB
gemma-7b.Q4_1.gguf	Q4_1	5.12GB
gemma-7b.Q5_0.gguf	Q5_0	5.57GB
gemma-7b.Q5_K_S.gguf	Q5_K_S	5.57GB
gemma-7b.Q5_K.gguf	Q5_K	5.72GB
gemma-7b.Q5_K_M.gguf	Q5_K_M	5.72GB
gemma-7b.Q5_1.gguf	Q5_1	6.02GB
gemma-7b.Q6_K.gguf	Q6_K	6.53GB

Original model description:
Repo model google/gemma-7b is gated. You must be authenticated to access it.