1234567device Apple M5; IQ2_S/Q2_0, T 1, 512 experts, tile TM 16 TN 32 TK 32 SG 4right-input layout: runs of 4 kplan: 10 tiles of 16, 160 padded rows for 10 entriesuseful GFLOP per layer 0.1 (padded rows 160 = 16.00x entries)ab bitwise (T=1): HS_memcmp=PASS YE_memcmp=PASS Y_memcmp=PASSdown A/B (T=1): A med=61.4 (min=58.0) | B med=61.7 (min=58.7) | diff med=+0.51% min=+1.15%