This is a MXFP4_MOE quantization of the model Ring-mini-sparse-2.0-exp

Added rope scaling to extend the context from 32k to 128k.

Downloads last month
23
GGUF
Model size
16B params
Architecture
bailingmoe2
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for noctrex/Ring-mini-sparse-2.0-exp-MXFP4_MOE-GGUF