Llamacpp imatrix Quantizations of gemma 2 9b it Using llama.cpp release b3389 for quantization. Original model: https://huggingface.co/google/gemma 2 9b it All quants made using imatrix option with dataset from here Prompt format Note that this model does not support a System prompt. Download a file (not the whole branch) from below: Filename Quant type File Size Split Description gemma 2 9b it f32.gguf f32 36.97GB false Full F32 weights. gemma 2 9b it Q8 0.gguf Q8 0 9.83GB false Extremely high quality, generally unneeded but max available quant. gemma 2 9b it Q6 K L.gguf Q6 K L 7.81GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . gemma 2 9b it Q6 K.gguf Q6 K 7.59GB false Very high quality, near perfect, recommended . gemma 2 9b it Q5 K L.gguf Q5 K L 6.87GB false Uses Q8 0 for embed and output weights. High quality, recommended . gemma 2 9b it Q5 K M.gguf Q5 K M 6.65GB false High quality, recommended . gemma 2 9b it Q5 K S.gguf Q5 K S 6.48GB false High quality, recommended . gemma 2 9b it Q4 K L.gguf Q4 K L 5.98GB false Uses Q8 0 for embed and output weights. Good quality, recommended . gemma 2 9b it Q4 K M.gguf Q4 K M 5.76GB false Goo…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy