Qwen3.5 122B (10B active)

User reports Qwen3.5 122B-A10B at 288.5 t/s prompt processing on an AMD Ryzen AI MAX+ 395 with Radeon 8060S graphics. Setup is llama.cpp b9843 with UD-Q6_K_XL, f16 K/V cache and flash attention, one participating Radeon with ngl=999 and 16 CPU threads. The 288.5 t/s figure is the stock batch2048/ubatch512 arm at depth 512, measured as 288.503604 +/- 2.290730 t/s; the same arm falls to 119.312542 t/s at depth 100000. Generation throughput and TTFT were not measured.