Trillion-Parameter MoE in a Box: Decoupling Memory Provisioning with High-Bandwidth Flash

Abstract

An MoE appliance for trillion-parameter models at low concurrency must host terabytes of weights on one node and serve prefill and decode with fixed resources. Combining operator analysis of two trillion-parameter MoE models, a measured expert routing trace, and agentic serving traces over multiple turns, we explore a design space spanning High-Bandwidth Flash (HBF) and DRAM configurations, bandwidth exposure, and near-data compute. We find that state bandwidth and HBF transport form two largely orthogonal knees and address two provisioning questions. Q1: Once weights move to HBF, what bandwidth-to-capacity ratio does DRAM require? With a 256-GB floor for the state tier, both models meet a $1.10\times$ completion time target at ratios of only $1.4$--$4.0~\mathrm{s}^{-1}$, roughly an order of magnitude below HBM3e's $33.3~\mathrm{s}^{-1}$. Q2: As HBF internal bandwidth scales with capacity, must bandwidth to the host scale proportionally? Six HBF packages expose 384~GB/s per package to the host, 2.30~TB/s aggregate and 62.5\% below the 6.14~TB/s full exposure reference, while more packages reduce required bandwidth per package at the same target.