Z.ai

GLM-4.5 Air

MoE

Pick a size: the video memory shown is the Q4_K_M file (the protocol's quantisation) plus about 1.5 GB for a 4,000-token context.

106B-A12B

> 32 GB
Parameters
110,5B · 12B active
Q4_K_M file
68,5 Go
Recommended VRAM
≥ 70,0 Go
Max context
131 072

Not measured yet

MoE (“30B-A3B”): all the memory of a 30B, but the speed of a model with 3B active parameters. “> 32 GB”: several cards, or part of the model in system memory (much slower).