Z.ai
GLM-4 0414
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.
9B
8 GB card- Parameters
- 9,4B
- Q4_K_M file
- 5,7 Go
- Recommended VRAM
- ≥ 7,2 Go
- Max context
- 32 768
Not measured yet
32B
24 GB card- Parameters
- 32,6B
- Q4_K_M file
- 18,3 Go
- Recommended VRAM
- ≥ 19,8 Go
- Max context
- 32 768
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).