Llamacpp imatrix Quantizations of MN 12B Mag Mell R1 Using llama.cpp release b4381 for quantization. Original model: https://huggingface.co/inflatebot/MN 12B Mag Mell R1 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 MN 12B Mag Mell R1 f16.gguf f16 24.50GB false Full F16 weights. MN 12B Mag Mell R1 Q8 0.gguf Q8 0 13.02GB false Extremely high quality, generally unneeded but max available quant. MN 12B Mag Mell R1 Q6 K L.gguf Q6 K L 10.38GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . MN 12B Mag Mell R1 Q6 K.gguf Q6 K 10.06GB false Very high quality, near perfect, recommended . MN 12B Mag Mell R1 Q5 K L.gguf Q5 K L 9.14GB false Uses Q8 0 for embed and output weights. High quality, recommended . MN 12B Mag Mell R1 Q5 K M.gguf Q5 K M 8.73GB false High quality, recommended . MN 12B Mag Mell R1 Q5 K S.gguf Q5 K S 8.52GB false High quality, recommended . MN 12B Mag Mell R1 Q4 K L.gguf Q4 K L 7.98GB false Uses Q8 0 for embed and output weights. Good quality, recommended . MN 12B Mag Mell R1 Q4 1.g…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy