This is a MXFP4_MOE quantization of the model MiniMax-M2-THRIFT-55 with an imatrix from mradermacher.

Download the latest llama.cpp to use it.

Keep in mind that this a coding model.

Downloads last month
305
GGUF
Model size
106B params
Architecture
minimax-m2
Hardware compatibility
Log In to view the estimation

4-bit

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

Model tree for noctrex/MiniMax-M2-THRIFT-55-MXFP4_MOE-GGUF

Quantized
(3)
this model