erikqu
/

Mixtral_7Bx4_MOE_24B-gguf

Inference Endpoints

Model card Files Files and versions Community

Original repo: https://huggingface.co/cloudyu/Mixtral_7Bx4_MOE_24B

This is the Q4_K_M version.

Model requires ~13G vram.

Downloads last month: 3

GGUF

Model size

24.2B params

Architecture

llama

4-bit

Inference API

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