Llamacpp imatrix Quantizations of MiniCPM V 2 6 Using llama.cpp release b3615 for quantization. Original model: https://huggingface.co/openbmb/MiniCPM V 2 6 All quants made using imatrix option with dataset from here Run them in LM Studio Prompt format What's new: Applying imatrix, should improve the text portion of the model Download a file (not the whole branch) from below: Filename Quant type File Size Split Description MiniCPM V 2 6 f16.gguf f16 15.23GB false Full F16 weights. MiniCPM V 2 6 Q8 0.gguf Q8 0 8.10GB false Extremely high quality, generally unneeded but max available quant. MiniCPM V 2 6 Q6 K L.gguf Q6 K L 6.52GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . MiniCPM V 2 6 Q6 K.gguf Q6 K 6.25GB false Very high quality, near perfect, recommended . MiniCPM V 2 6 Q5 K L.gguf Q5 K L 5.78GB false Uses Q8 0 for embed and output weights. High quality, recommended . MiniCPM V 2 6 Q5 K M.gguf Q5 K M 5.44GB false High quality, recommended . MiniCPM V 2 6 Q5 K S.gguf Q5 K S 5.31GB false High quality, recommended . MiniCPM V 2 6 Q4 K L.gguf Q4 K L 5.08GB false Uses Q8 0 for embed and output weights. Good quality, recommended . MiniCP…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy