Run with llama.cpp

llama-cli -m  GLM-4.5-Air-MXFP4_MOE-00001-of-00005.gguf
Downloads last month
205
GGUF
Model size
110B params
Architecture
glm4moe
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 Face314/GLM-4.5-Air-MXFP4_MOE

Quantized
(59)
this model