Llamacpp imatrix Quantizations of QwQ 32B Preview Using llama.cpp release b4191 for quantization. Original model: https://huggingface.co/Qwen/QwQ 32B Preview 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 QwQ 32B Preview bf16.gguf bf16 65.54GB true Full BF16 weights. QwQ 32B Preview Q8 0.gguf Q8 0 34.82GB false Extremely high quality, generally unneeded but max available quant. QwQ 32B Preview Q6 K L.gguf Q6 K L 27.26GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . QwQ 32B Preview Q6 K.gguf Q6 K 26.89GB false Very high quality, near perfect, recommended . QwQ 32B Preview Q5 K L.gguf Q5 K L 23.74GB false Uses Q8 0 for embed and output weights. High quality, recommended . QwQ 32B Preview Q5 K M.gguf Q5 K M 23.26GB false High quality, recommended . QwQ 32B Preview Q5 K S.gguf Q5 K S 22.64GB false High quality, recommended . QwQ 32B Preview Q4 K L.gguf Q4 K L 20.43GB false Uses Q8 0 for embed and output weights. Good quality, recommended . QwQ 32B Preview Q4 K M.gguf Q4 K M 19.85GB false Good q…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy