Dual-GPU inference may depend on PCIe x8/x4 versus x8/x8
The Biostar Z890 Valkyrie has three PCIe 5.0 slots connected directly to the CPU. With one card, it can run at x16; with two cards, it can run at x8/x8; with three cards, it can split into x8/x4/x4.
A dual-GPU setup for would normally aim to use x8/x8. Adding a SATA expansion card to the bottom PCIe slot could reduce the middle GPU slot to x4.
The practical question is whether running two GPUs at x8/x4 would noticeably slow . The concern applies both when the whole model fits inside VRAM and when partial is needed.
Key points
- The can split PCIe 5.0 lanes as x16, x8/x8, or x8/x4/x4.
- Adding a SATA expansion card may drop the second GPU slot from x8 to x4.
- The main issue is whether x8/x4 slows dual-GPU compared with x8/x8.
- The answer may differ when the model fully fits in VRAM versus when partial is used.
- For local AI cost savings, PCIe slot layout can matter as much as the number of GPUs.