Llamacpp imatrix Quantizations of Codestral 22B v0.1 Using llama.cpp release b3024 for quantization. Original model: https://huggingface.co/mistralai/Codestral 22B v0.1 All quants made using imatrix option with dataset from here Prompt format Download a file (not the whole branch) from below: Filename Quant type File Size Description Codestral 22B v0.1 Q8 0.gguf Q8 0 23.64GB Extremely high quality, generally unneeded but max available quant. Codestral 22B v0.1 Q6 K.gguf Q6 K 18.25GB Very high quality, near perfect, recommended . Codestral 22B v0.1 Q5 K M.gguf Q5 K M 15.72GB High quality, recommended . Codestral 22B v0.1 Q5 K S.gguf Q5 K S 15.32GB High quality, recommended . Codestral 22B v0.1 Q4 K M.gguf Q4 K M 13.34GB Good quality, uses about 4.83 bits per weight, recommended . Codestral 22B v0.1 Q4 K S.gguf Q4 K S 12.66GB Slightly lower quality with more space savings, recommended . Codestral 22B v0.1 IQ4 XS.gguf IQ4 XS 11.93GB Decent quality, smaller than Q4 K S with similar performance, recommended . Codestral 22B v0.1 Q3 K L.gguf Q3 K L 11.73GB Lower quality but usable, good for low RAM availability. Codestral 22B v0.1 Q3 K M.gguf Q3 K M 10.75GB Even lower quality. Codestral 2…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy