Llamacpp imatrix Quantizations of magnum 12b v2.5 kto Using llama.cpp release b3583 for quantization. Original model: https://huggingface.co/anthracite org/magnum 12b v2.5 kto 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 12b v2.5 kto f32.gguf f32 49.00GB false Full F32 weights. magnum 12b v2.5 kto Q8 0.gguf Q8 0 13.02GB false Extremely high quality, generally unneeded but max available quant. magnum 12b v2.5 kto Q6 K L.gguf Q6 K L 10.38GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . magnum 12b v2.5 kto Q6 K.gguf Q6 K 10.06GB false Very high quality, near perfect, recommended . magnum 12b v2.5 kto Q5 K L.gguf Q5 K L 9.14GB false Uses Q8 0 for embed and output weights. High quality, recommended . magnum 12b v2.5 kto Q5 K M.gguf Q5 K M 8.73GB false High quality, recommended . magnum 12b v2.5 kto Q5 K S.gguf Q5 K S 8.52GB false High quality, recommended . magnum 12b v2.5 kto Q4 K L.gguf Q4 K L 7.98GB false Uses Q8 0 for embed and output weights. Good quality, recommended . magnum 12b…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy