If your motivation is to be able to run the model on-prem, with parallelism for API service throughput (rather than on a single device), you don't need large memory GPUs or intensive memory swapping.
You can architect it as cheaper, low-memory GPUs, one expert submodel per GPU, transferring state over the network between the GPUs for each token. They run in parallel by overlapping API calls (and in future by other model architecture changes).
Th MoE model reduces inter-GPU communication requirements for splitting the model, in an addition to reducing GPU processing requirements, compared with a non-MoE model with the same number of weights. There are pros and cons to this splitting, but you can see the general trend.
You can architect it as cheaper, low-memory GPUs, one expert submodel per GPU, transferring state over the network between the GPUs for each token. They run in parallel by overlapping API calls (and in future by other model architecture changes).
Th MoE model reduces inter-GPU communication requirements for splitting the model, in an addition to reducing GPU processing requirements, compared with a non-MoE model with the same number of weights. There are pros and cons to this splitting, but you can see the general trend.