Mistral AI

Magistral Small

reasoning

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.

24B

16 GB card

Parameters: 24B
Q4_K_M file: 13,3 Go
Recommended VRAM: ≥ 14,8 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).