gelukuMLG
/

FimLotus-2x10.7B-GGUF

This model is a clownmoe/frankenmoe consisting of the following two models:

This is an experimental model so it might have jank.

GGUF

Model size

19.2B params

Architecture

llama

4-bit

Inference Examples

Inference API (serverless) is not available, repository is disabled.