IBM
Granite 4.1
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.
3B
8 GB card- Parameters
- 3,4B
- Q4_K_M file
- 2,0 Go
- Recommended VRAM
- ≥ 3,5 Go
- Max context
- 131 072
Not measured yet
8B
8 GB card- Parameters
- 8,8B
- Q4_K_M file
- 5,2 Go
- Recommended VRAM
- ≥ 6,7 Go
- Max context
- 131 072
Not measured yet
30B
24 GB card- Parameters
- 28,9B
- Q4_K_M file
- 16,6 Go
- Recommended VRAM
- ≥ 18,1 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).