Llamacpp imatrix Quantizations of magnum v4 27b Using llama.cpp release b3930 for quantization. Original model: https://huggingface.co/anthracite org/magnum v4 27b All quants made using imatrix option with dataset from here Run them in LM Studio Prompt format Download a file (not the whole branch) from below: Filename Quant type File Size Split Description magnum v4 27b f16.gguf f16 54.46GB true Full F16 weights. magnum v4 27b Q8 0.gguf Q8 0 28.94GB false Extremely high quality, generally unneeded but max available quant. magnum v4 27b Q6 K L.gguf Q6 K L 22.63GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . magnum v4 27b Q6 K.gguf Q6 K 22.34GB false Very high quality, near perfect, recommended . magnum v4 27b Q5 K L.gguf Q5 K L 19.69GB false Uses Q8 0 for embed and output weights. High quality, recommended . magnum v4 27b Q5 K M.gguf Q5 K M 19.41GB false High quality, recommended . magnum v4 27b Q5 K S.gguf Q5 K S 18.88GB false High quality, recommended . magnum v4 27b Q4 K L.gguf Q4 K L 16.93GB false Uses Q8 0 for embed and output weights. Good quality, recommended . magnum v4 27b Q4 K M.gguf Q4 K M 16.65GB false Good quality, default…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy