DeepSeek

DeepSeek V4 Flash

MoE

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.

Flash

> 32 GB

Parameters: 304,2B
MXFP4 file: 145,6 Go
Recommended VRAM: ≥ 147,1 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).