Local Qwen 3.6 and GLM 5.2 Inference Rigs

@watchmedropship hit ~130 tok/s on Qwen 3.6 27B dense and 35B MoE with a 128GB M5 anonymous plus DGX Spark, tool calling intact. @jcartu weighed in on FP8 vs BF16, MoE math (35B MoE ≈ 8B active, needs ~120-150B dense to…