v000000 / Typhon-Mixtral-v1-imatrix-v2.Q6_K-GGUF
Other460Updated Sep 26, 2024
Downloads
46
Likes
0
Last updated
Sep 26, 2024
License
cc-by-nc-4.0
Contains: Q6K GGUF (imatrix) Can fit in 16GB VRAM+32GB RAM, nctx 8k, 12 layers, blas 1024, reading speed generation
Tasks & library
- transformers
Tags
- transformers
- gguf
- merge
- mixtral
- mistral
- llama.cpp
Technical specifications
ParametersNot available
Librarytransformers
LanguagesNot available
Base modelmistralai/Mixtral-8x7B-v0.1
Licensecc-by-nc-4.0