Llamacpp imatrix Quantizations of Fara1.5 27B by microsoft Using llama.cpp release b10087 for quantization. Original model: https://huggingface.co/microsoft/Fara1.5 27B 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 Fara1.5 27B bf16.gguf bf16 53.81GB true Full BF16 weights. Fara1.5 27B Q8 0.gguf Q8 0 28.67GB false Extremely high quality, generally unneeded but max available quant. Fara1.5 27B Q6 K L.gguf Q6 K L 23.84GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . Fara1.5 27B Q6 K.gguf Q6 K 23.22GB false Very high quality, near perfect, recommended . Fara1.5 27B Q5 K L.gguf Q5 K L 21.30GB false Uses Q8 0 for embed and output weights. High quality, recommended . Fara1.5 27B Q5 K M.gguf Q5 K M 20.51GB false High quality, recommended . Fara1.5 27B Q5 K S.gguf Q5 K S 19.44GB false High quality, recommen…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy