48 GiB aggregate

The two-GPU route

A conditional path to a larger model when one card is too small.

What to plan for

GPUs
Two supported 24 GiB GPUs; check the runtime’s model-splitting support.
Platform
A motherboard with appropriate slot spacing and PCIe connectivity.
Memory & storage
Plan enough system RAM to load and stage the model; 128 GiB is a useful capacity to evaluate.
Power & cooling
Two RTX 3090 cards can account for 700 W of board power alone. Engineer for the entire system.

Your first run

  1. Estimate aggregate memory, then verify that individual layers and buffers fit on each device.
  2. Configure the actual split explicitly and inspect device-level allocations.
  3. Test sustained inference and compare against a single higher-memory alternative.

The tradeoff

This is a configuration concept, not a compatibility-certified parts list. More components, heat and runtime complexity may outweigh an apparent used-GPU saving.

These are component selection criteria, not a verified bill of materials. Check compatibility, current prices, power and cooling before purchasing. The examples assume Q4 weight precision, 8K context, one request and FP16 KV cache.