Llamacpp imatrix Quantizations of Yi Coder 1.5B Chat Using llama.cpp release b3658 for quantization. Original model: https://huggingface.co/01 ai/Yi Coder 1.5B Chat All quants made using imatrix option with dataset from here Run them in LM Studio Prompt format What's new: Fix tokenizer Download a file (not the whole branch) from below: Filename Quant type File Size Split Description Yi Coder 1.5B Chat f16.gguf f16 2.95GB false Full F16 weights. Yi Coder 1.5B Chat Q8 0.gguf Q8 0 1.57GB false Extremely high quality, generally unneeded but max available quant. Yi Coder 1.5B Chat Q6 K L.gguf Q6 K L 1.34GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . Yi Coder 1.5B Chat Q6 K.gguf Q6 K 1.28GB false Very high quality, near perfect, recommended . Yi Coder 1.5B Chat Q5 K L.gguf Q5 K L 1.18GB false Uses Q8 0 for embed and output weights. High quality, recommended . Yi Coder 1.5B Chat Q5 K M.gguf Q5 K M 1.10GB false High quality, recommended . Yi Coder 1.5B Chat Q4 K L.gguf Q4 K L 1.06GB false Uses Q8 0 for embed and output weights. Good quality, recommended . Yi Coder 1.5B Chat Q5 K S.gguf Q5 K S 1.05GB false High quality, recommended . Yi Coder…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy