q4_k_s quant for https://huggingface.co/tdrussell/Mixtral-8x22B-Capyboros-v1. These files are split using the gguf-split tool. If you want to recombine them to single file, you MUST use that tool, NOT cat.

GGUF

Model size

141B params

Architecture

llama

4-bit

Inference API

Unable to determine this model's library. Check the docs .