Use cases
tool-use
Summary
User reports Qwen3.8 27B at around 32 t/s on 2x RTX 3060 12GB with tensor split 1,1 after moving to an x470 SLI motherboard running both cards at x8.
Previously, with one card at x16 and the other at x1 on a B550 board, the user got 11-16 t/s in layer split mode.
The tensor-split run eventually gets stuck in loops, including repeated tool calls and endless question marks in thinking, which did not happen in layer split mode.