About weighted/imatrix quants of https://huggingface.co/zmzfpc/crane 30b For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/crane 30b GGUF Usage If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi part files. Provided Quants (sorted by size, not necessarily quality. IQ quants are often preferable over similar sized non IQ quants) Link Type Size/GB Notes : : : : GGUF imatrix 0.2 imatrix file (for creating your own quants) GGUF i1 IQ1 S 6.5 for the desperate GGUF i1 IQ1 M 7.2 mostly desperate GGUF i1 IQ2 XXS 8.3 GGUF i1 IQ2 XS 9.2 GGUF i1 IQ2 S 9.4 GGUF i1 IQ2 M 10.3 GGUF i1 Q2 K S 10.6 very low quality GGUF i1 Q2 K 11.4 IQ3 XXS probably better GGUF i1 IQ3 XXS 11.9 lower quality GGUF i1 IQ3 XS 12.7 GGUF i1 Q3 K S 13.4 IQ3 XS probably better GGUF i1 IQ3 S 13.4 beats Q3 K GGUF i1 IQ3 M 13.6 GGUF i1 Q3 K M 14.8 IQ3 S probably better GGUF i1 Q3 K L 16.0 IQ3 M probably better GGUF i1 IQ4 XS 16.5 GGUF i1 Q4 0 17.5 fast, low quality GGUF i1 Q4 K S 17.6 optimal size/speed/quality GGUF i1 Q4 K M 18.7 fast, recommended…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy