This is a MXFP4_MOE quantization of the model Trinity-Mini

This is a imatrix version, based on the imatrix from bartowski.

Downloads last month
246
GGUF
Model size
26B params
Architecture
afmoe
Hardware compatibility
Log In to view the estimation

4-bit

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

Model tree for noctrex/Trinity-Mini-MXFP4_MOE-GGUF

Quantized
(18)
this model