[alightsoul]

Because you need GPUs to run it fast enough for an attack to be effective. 8 GPU servers with enough VRAM are that expensive.

[lcampbell]

FWIW, you can get a 16x RTX 6000 Pro setup running for significantly less than that. Even considering the electrical hookup fees (it’s a lot of power and cooling). Home ownership might push you into the original quote though.

[walrus01]

Kimi K3 is in no way going to fit in 96GB RAM * 16 units (1536GB) unless badly quantized and with a small amount of context.

[johndough]

Why not? The model is 2.8T parameters with native MXFP4, which is 1400GB.

[alightsoul]

I would figure it needs a lot of kV cache and context size which can be much bigger than the model itself