Qwen3.5 27B
on 2× heterogeneous GPUs total: Radeon 8060S + NVIDIA RTX 5070 Ti 16GB · llama.cpp / Vulkan (build unreported)
Summary
User reports Qwen3.5-27B at 12.4 t/s generation and 281 t/s prompt processing on a Minisforum MS-S1 Max with Radeon 8060S and an RTX 5070 Ti over OCuLink.
Setup is llama-bench with UD-Q4_K_XL, -ngl 99 -fa 1, and a 9/1 Radeon-to-RTX tensor split, PP512 and TG128 phases.
The 9/1 split measured 12.43 +/- 0.03 t/s TG128 and 280.95 +/- 10.11 t/s PP512; the all-APU 10/0 endpoint gave 11.89 t/s, and 0/10 failed with ErrorOutOfDeviceMemory.