Views
No views yet
llama.cpp (llama-quantize) from an F16 GGUF converted directly from the base safetensors.| File | Quant | Size |
|---|---|---|
gemma-4-12B-it-uncensored-opus4.7-cot-Q2_K.gguf | Q2_K | 4.83 GB |
gemma-4-12B-it-uncensored-opus4.7-cot-Q3_K_M.gguf | Q3_K_M | 6.09 GB |
gemma-4-12B-it-uncensored-opus4.7-cot-Q4_K_M.gguf | Q4_K_M | 7.38 GB |
gemma-4-12B-it-uncensored-opus4.7-cot-Q5_K_M.gguf | Q5_K_M | 8.55 GB |
gemma-4-12B-it-uncensored-opus4.7-cot-Q6_K.gguf | Q6_K | 9.79 GB |
gemma-4-12B-it-uncensored-opus4.7-cot-Q8_0.gguf | Q8_0 | 12.67 GB |
gemma-4-12B-it-uncensored-opus4.7-cot-F16.gguf | F16 | 23.83 GB |
llama-cli -hf Rangle2/gemma-4-12B-it-uncensored-opus4.7-cot-GGUF:Q4_K_M