Llamacpp Static Quantizations of granite embedding 107m multilingual Using llama.cpp release b4381 for quantization. Original model: https://huggingface.co/ibm granite/granite embedding 107m multilingual Run them in LM Studio Prompt format No prompt format found, check original model page What's new: Fix tokenizer Download a file (not the whole branch) from below: Filename Quant type File Size Split Description granite embedding 107m multilingual f16.gguf f16 0.22GB false Full F16 weights. granite embedding 107m multilingual Q8 0.gguf Q8 0 0.12GB false Extremely high quality, generally unneeded but max available quant. granite embedding 107m multilingual Q6 K L.gguf Q6 K L 0.12GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . granite embedding 107m multilingual Q6 K.gguf Q6 K 0.12GB false Very high quality, near perfect, recommended . granite embedding 107m multilingual Q5 K L.gguf Q5 K L 0.12GB false Uses Q8 0 for embed and output weights. High quality, recommended . granite embedding 107m multilingual Q5 K M.gguf Q5 K M 0.12GB false High quality, recommended . granite embedding 107m multilingual Q5 K S.gguf Q5 K S 0.12GB false High qu…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy