Quantization made by Richard Erkhov.
codegemma-7b-it - GGUF
- Model creator: https://huggingface.co/google/
- Original model: https://huggingface.co/google/codegemma-7b-it/
| Name | Quant method | Size |
|---|---|---|
| codegemma-7b-it.Q2_K.gguf | Q2_K | 3.24GB |
| codegemma-7b-it.IQ3_XS.gguf | IQ3_XS | 3.54GB |
| codegemma-7b-it.IQ3_S.gguf | IQ3_S | 3.71GB |
| codegemma-7b-it.Q3_K_S.gguf | Q3_K_S | 3.71GB |
| codegemma-7b-it.IQ3_M.gguf | IQ3_M | 3.82GB |
| codegemma-7b-it.Q3_K.gguf | Q3_K | 4.07GB |
| codegemma-7b-it.Q3_K_M.gguf | Q3_K_M | 4.07GB |
| codegemma-7b-it.Q3_K_L.gguf | Q3_K_L | 4.39GB |
| codegemma-7b-it.IQ4_XS.gguf | IQ4_XS | 4.48GB |
| codegemma-7b-it.Q4_0.gguf | Q4_0 | 4.67GB |
| codegemma-7b-it.IQ4_NL.gguf | IQ4_NL | 4.69GB |
| codegemma-7b-it.Q4_K_S.gguf | Q4_K_S | 4.7GB |
| codegemma-7b-it.Q4_K.gguf | Q4_K | 4.96GB |
| codegemma-7b-it.Q4_K_M.gguf | Q4_K_M | 4.96GB |
| codegemma-7b-it.Q4_1.gguf | Q4_1 | 5.12GB |
| codegemma-7b-it.Q5_0.gguf | Q5_0 | 5.57GB |
| codegemma-7b-it.Q5_K_S.gguf | Q5_K_S | 5.57GB |
| codegemma-7b-it.Q5_K.gguf | Q5_K | 5.72GB |
| codegemma-7b-it.Q5_K_M.gguf | Q5_K_M | 5.72GB |
| codegemma-7b-it.Q5_1.gguf | Q5_1 | 6.02GB |
| codegemma-7b-it.Q6_K.gguf | Q6_K | 6.53GB |
Original model description: Repo model google/codegemma-7b-it is gated. You must be authenticated to access it.