Llamacpp imatrix Quantizations of Laguna XS 2.1 by poolside Using llama.cpp release b10087 for quantization. Original model: https://huggingface.co/poolside/Laguna XS 2.1 All quants made using imatrix option with dataset from here Run them in your choice of tools: llama.cpp ramalama LM Studio koboldcpp Jan AI Text Generation Web UI LoLLMs Atomic Chat Note: if it's a newly supported model, you may need to wait for an update from the developers. Prompt format Download a file (not the whole branch) from below: Filename Quant type File Size Split Description Laguna XS 2.1 bf16.gguf bf16 66.93GB true Full BF16 weights. Laguna XS 2.1 Q8 0.gguf Q8 0 35.60GB false Extremely high quality, generally unneeded but max available quant. Laguna XS 2.1 Q6 K L.gguf Q6 K L 29.14GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . Laguna XS 2.1 Q6 K.gguf Q6 K 29.04GB false Very high quality, near perfect, recommended . Laguna XS 2.1 Q5 K L.gguf Q5 K L 24.13GB false Uses Q8 0 for embed and output weights. High quality, recommended . Laguna XS 2.1 Q5 K M.gguf Q5 K M 24.01GB false High quality, recommended . Laguna XS 2.1 Q5 K S.gguf Q5 K S 23.23GB false High q…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy