Llamacpp imatrix Quantizations of Tess 4 27B by migtissera Using llama.cpp release b9918 for quantization. Original model: https://huggingface.co/migtissera/Tess 4 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 Tess 4 27B bf16.gguf bf16 54.66GB true Full BF16 weights. Tess 4 27B Q8 0.gguf Q8 0 29.12GB false Extremely high quality, generally unneeded but max available quant. Tess 4 27B Q6 K L.gguf Q6 K L 24.08GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . Tess 4 27B Q6 K.gguf Q6 K 23.46GB false Very high quality, near perfect, recommended . Tess 4 27B Q5 K L.gguf Q5 K L 21.54GB false Uses Q8 0 for embed and output weights. High quality, recommended . Tess 4 27B Q5 K M.gguf Q5 K M 20.75GB false High quality, recommended . Tess 4 27B Q5 K S.gguf Q5 K S 19.68GB false High quality, recommended . Te…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy