Llamacpp imatrix Quantizations of gemma 2 2b it abliterated Using llama.cpp release b3496 for quantization. Original model: https://huggingface.co/IlyaGusev/gemma 2 2b it abliterated All quants made using imatrix option with dataset from here Run them in LM Studio 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 2b it abliterated f32.gguf f32 10.46GB false Full F32 weights. gemma 2 2b it abliterated Q8 0.gguf Q8 0 2.78GB false Extremely high quality, generally unneeded but max available quant. gemma 2 2b it abliterated Q6 K L.gguf Q6 K L 2.29GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . gemma 2 2b it abliterated Q6 K.gguf Q6 K 2.15GB false Very high quality, near perfect, recommended . gemma 2 2b it abliterated Q5 K L.gguf Q5 K L 2.07GB false Uses Q8 0 for embed and output weights. High quality, recommended . gemma 2 2b it abliterated Q5 K M.gguf Q5 K M 1.92GB false High quality, recommended . gemma 2 2b it abliterated Q5 K S.gguf Q5 K S 1.88GB false High quality, recommended . gemma 2 2b it abliterated Q4 K…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy