Meta

Llama 3.1

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.

8B

8 GB card
Parameters
8B
Q4_K_M file
4,6 Go
Recommended VRAM
≥ 6,1 Go
Max context
131 072

Measured on 2 cards · 149 tok/s (RTX 5070 Ti)

70B

> 32 GB
Parameters
70,6B
Q4_K_M file
39,6 Go
Recommended VRAM
≥ 41,1 Go
Max context
131 072

Not measured yet

405B

> 32 GB
Parameters
405,9B
Q4_K_M file
228,8 Go
Recommended VRAM
≥ 230,3 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).