Llamacpp imatrix Quantizations of Nex N2 Pro by nex agi Using llama.cpp release b9590 for quantization. Original model: https://huggingface.co/nex agi/Nex N2 Pro All quants made using imatrix option with dataset from here Run them in your choice of tools: llama.cpp ramalama LM Studio koboldcpp Jan AI Text Generation Web UI LoLLMs Note: if it's a newly supported model, you may need to wait for an update from the developers. Prompt format Download a file (not the whole branch) from below: Filename Quant type File Size Split Description Nex N2 Pro Q8 0.gguf Q8 0 421.51GB true Extremely high quality, generally unneeded but max available quant. Nex N2 Pro Q6 K.gguf Q6 K 342.39GB true Very high quality, near perfect, recommended . Nex N2 Pro Q5 K M.gguf Q5 K M 283.26GB true High quality, recommended . Nex N2 Pro Q5 K S.gguf Q5 K S 273.99GB true High quality, recommended . Nex N2 Pro Q4 1.gguf Q4 1 249.10GB true Legacy format, similar performance to Q4 K S but with improved tokens/watt on Apple silicon. Nex N2 Pro Q4 K L.gguf Q4 K L 242.56GB true Uses Q8 0 for embed and output weights. Good quality, recommended . Nex N2 Pro Q4 K M.gguf Q4 K M 241.81GB true Good quality, default size for m…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy