Llamacpp imatrix Quantizations of Yi 1.5 9B Chat Using llama.cpp release b2854 for quantization. Original model: https://huggingface.co/01 ai/Yi 1.5 9B Chat All quants made using imatrix option with dataset provided by Kalomaze here Prompt format Download a file (not the whole branch) from below: Filename Quant type File Size Description Yi 1.5 9B Chat Q8 0.gguf Q8 0 9.38GB Extremely high quality, generally unneeded but max available quant. Yi 1.5 9B Chat Q6 K.gguf Q6 K 7.24GB Very high quality, near perfect, recommended . Yi 1.5 9B Chat Q5 K M.gguf Q5 K M 6.25GB High quality, recommended . Yi 1.5 9B Chat Q5 K S.gguf Q5 K S 6.10GB High quality, recommended . Yi 1.5 9B Chat Q4 K M.gguf Q4 K M 5.32GB Good quality, uses about 4.83 bits per weight, recommended . Yi 1.5 9B Chat Q4 K S.gguf Q4 K S 5.07GB Slightly lower quality with more space savings, recommended . Yi 1.5 9B Chat IQ4 NL.gguf IQ4 NL 5.04GB Decent quality, slightly smaller than Q4 K S with similar performance recommended . Yi 1.5 9B Chat IQ4 XS.gguf IQ4 XS 4.78GB Decent quality, smaller than Q4 K S with similar performance, recommended . Yi 1.5 9B Chat Q3 K L.gguf Q3 K L 4.69GB Lower quality but usable, good for low RAM av…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy