Qwen3.6 35B (3B active) Claude-4.6-Opus-Reasoning-Distilled

User reports ik_llama.cpp at 118.79 t/s prompt processing and 10.40 t/s generation on a GTX 1660 Super 6GB with Qwen3.6-35B-A3B IQ4_XS at 131072 context. Setup is ik_llama.cpp with --cpu-moe, -ngl 999, -amb 2048, -rtr and --prompt-cache-all on an AMD Ryzen 7 5800X. Mainline llama.cpp on the same machine reached 239.81 t/s PP and 15.69 t/s TG, so ik_llama.cpp is about 2x slower on PP and 1.5x slower on TG. User suspects --prompt-cache-all, -rtr or -amb 2048 may be responsible.