Llamacpp imatrix Quantizations of glm 4 9b chat Using llama.cpp release b3615 for quantization. Original model: https://huggingface.co/THUDM/glm 4 9b chat 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 glm 4 9b chat Q8 0.gguf Q8 0 9.99GB false Extremely high quality, generally unneeded but max available quant. glm 4 9b chat Q6 K L.gguf Q6 K L 8.56GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . glm 4 9b chat Q6 K.gguf Q6 K 8.26GB false Very high quality, near perfect, recommended . glm 4 9b chat Q5 K L.gguf Q5 K L 7.53GB false Uses Q8 0 for embed and output weights. High quality, recommended . glm 4 9b chat Q5 K M.gguf Q5 K M 7.14GB false High quality, recommended . glm 4 9b chat Q4 K L.gguf Q4 K L 6.71GB false Uses Q8 0 for embed and output weights. Good quality, recommended . glm 4 9b chat Q5 K S.gguf Q5 K S 6.69GB false High quality, recommended . glm 4 9b chat Q4 K M.gguf Q4 K M 6.25GB false Good quality, default size for must use cases, recommended . glm 4 9b chat Q3 K XL.gguf Q3 K XL…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy