[NightlyDev]

The full deepseek R1 model needs more memory than 512GB. The model is 720GB alone. You can run a quantized version on it, but not the full model.

[summarity]

You can chain multiple Mac Studios using exo for inference, you'd "only" need two of these. There's a bottleneck in the RMA speed over TB5, but this may not matter as much for a MoE model.