InferenceIllusionist / Mixtral-8x22B-v0.1-iMat-GGUF
Other1.2K0Updated Apr 24, 2024
Downloads
1.2K
Likes
0
Last updated
Apr 24, 2024
License
Not available
Quantized from fp32 with love. If you're on the latest release of llama.cpp you should no longer need to combine files before loading Importance Matrix .dat file created using Q8 quant and groupsmerged.txt
Tags
- gguf
- merge
- mixtral
- iMat
Technical specifications
ParametersNot available
LibraryNot available
LanguagesNot available
LicenseNot available