Llamacpp imatrix Quantizations of Rocinante X 12B v1 by TheDrummer Using llama.cpp release b7779 for quantization. Original model: https://huggingface.co/TheDrummer/Rocinante X 12B v1 All quants made using imatrix option with dataset from here Run them in your choice of tools: llama.cpp LM Studio koboldcpp Jan AI Text Generation Web UI LoLLMs 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 Rocinante X 12B v1 bf16.gguf bf16 24.50GB false Full BF16 weights. Rocinante X 12B v1 Q8 0.gguf Q8 0 13.02GB false Extremely high quality, generally unneeded but max available quant. Rocinante X 12B v1 Q6 K L.gguf Q6 K L 10.38GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . Rocinante X 12B v1 Q6 K.gguf Q6 K 10.06GB false Very high quality, near perfect, recommended . Rocinante X 12B v1 Q5 K L.gguf Q5 K L 9.14GB false Uses Q8 0 for embed and output weights. High quality, recommended . Rocinante X 12B v1 Q5 K M.gguf Q5 K M 8.73GB false High quality, recommended . Rocinante X 12B v1 Q5 K S.gguf Q…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy