Meta

Llama 4

MoEvision

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.

Scout 109B-A17B

> 32 GB
Parameters
108,6B · 17B active
Q4_K_M file
62,9 Go
Recommended VRAM
≥ 64,4 Go
Max context
10 485 760

Not measured yet

Maverick 400B-A17B

> 32 GB
Parameters
401,6B · 17B active
Q4_K_M file
226,1 Go
Recommended VRAM
≥ 227,6 Go
Max context
1 048 576

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).