Mistral AI

Mistral Nemo

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.

12B

12 GB card

Parameters: 12,2B
Q4_K_M file: 7,0 Go
Recommended VRAM: ≥ 8,5 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).