Llamacpp imatrix Quantizations of Lexi Llama 3 8B Uncensored Using llama.cpp release b2714 for quantization. Original model: https://huggingface.co/Orenguteng/Lexi Llama 3 8B Uncensored All quants made using imatrix option with dataset provided by Kalomaze here Prompt format Download a file (not the whole branch) from below: Filename Quant type File Size Description Lexi Llama 3 8B Uncensored Q8 0.gguf Q8 0 8.54GB Extremely high quality, generally unneeded but max available quant. Lexi Llama 3 8B Uncensored Q6 K.gguf Q6 K 6.59GB Very high quality, near perfect, recommended . Lexi Llama 3 8B Uncensored Q5 K M.gguf Q5 K M 5.73GB High quality, recommended . Lexi Llama 3 8B Uncensored Q5 K S.gguf Q5 K S 5.59GB High quality, recommended . Lexi Llama 3 8B Uncensored Q4 K M.gguf Q4 K M 4.92GB Good quality, uses about 4.83 bits per weight, recommended . Lexi Llama 3 8B Uncensored Q4 K S.gguf Q4 K S 4.69GB Slightly lower quality with more space savings, recommended . Lexi Llama 3 8B Uncensored IQ4 NL.gguf IQ4 NL 4.67GB Decent quality, slightly smaller than Q4 K S with similar performance recommended . Lexi Llama 3 8B Uncensored IQ4 XS.gguf IQ4 XS 4.44GB Decent quality, smaller than Q4 K S w…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy