Llamacpp imatrix Quantizations of Llama 3.2 3B Instruct Using llama.cpp release b3821 for quantization. Original model: https://huggingface.co/meta llama/Llama 3.2 3B Instruct 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 Llama 3.2 3B Instruct f16.gguf f16 6.43GB false Full F16 weights. Llama 3.2 3B Instruct Q8 0.gguf Q8 0 3.42GB false Extremely high quality, generally unneeded but max available quant. Llama 3.2 3B Instruct Q6 K L.gguf Q6 K L 2.74GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . Llama 3.2 3B Instruct Q6 K.gguf Q6 K 2.64GB false Very high quality, near perfect, recommended . Llama 3.2 3B Instruct Q5 K L.gguf Q5 K L 2.42GB false Uses Q8 0 for embed and output weights. High quality, recommended . Llama 3.2 3B Instruct Q5 K M.gguf Q5 K M 2.32GB false High quality, recommended . Llama 3.2 3B Instruct Q5 K S.gguf Q5 K S 2.27GB false High quality, recommended . Llama 3.2 3B Instruct Q4 K L.gguf Q4 K L 2.11GB false Uses Q8 0 for embed and output weights. Good quality, recommended .…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy