Top Server GPUs Ranked by FP16 FLOPS of Vector(Shader/CUDA) cores

This is NOT a ranking of gaming performance, it's a ranking for AI workloads.
This is NOT a ranking of processors—many of them may be missing since their specifications aren’t available. If you know them, feel free to comment.
This is NOT a ranking of actual task performances, as they may vary due to many factors like thermal throttling, driver support, and framework compatibility...

133.80 T

3.36 TB/s

122.60 T

864 GB/s

#3

48 GB
NVIDIA L40

90.52 T

864 GB/s

90.50 T

576 GB/s

77.97 T

2.04 TB/s

77.97 T

1.94 TB/s

65.13 T

320 GB/s

63.90 T

576 GB/s

55.30 T

504 GB/s

52.43 T

3.28 TB/s

44.44 T

2.46 TB/s

40.55 T

512 GB/s

39.98 T

288 GB/s

38.71 T

768 GB/s

37.42 T

695 GB/s

35.64 T

512 GB/s

32.06 T

512 GB/s

31.33 T

898 GB/s

30.21 T

512 GB/s

29.49 T

1.02 TB/s

28.70 T

3.70 TB/s

28.18 T

825 GB/s

28.18 T

1.02 TB/s

26.82 T

1.02 TB/s

24.58 T

483 GB/s

24.58 T

436 GB/s

24.37 T

172 GB/s

24.10 T

300 GB/s

24.05 T

512 GB/s

22.22 T

1.23 TB/s

21.50 T

512 GB/s

21.50 T

512 GB/s

21.22 T

732 GB/s

20.89 T

448 GB/s

20.31 T

256 GB/s

18.49 T

224 GB/s

17.33 T

448 GB/s

15.35 T

384 GB/s

14.75 T

402 GB/s

14.58 T

224 GB/s

12.44 T

384 GB/s

11.71 T

394 GB/s

10.80 T

224 GB/s

10.80 T

224 GB/s

10.45 T

224 GB/s

9.27 T

224 GB/s

8.91 T

192 GB/s

8.19 T

512 GB/s

8.19 T

512 GB/s

7.13 T

128 GB/s

6.40 T

192 GB/s

6.40 T

192 GB/s

6.27 T

64 GB/s

5.73 T

224 GB/s

5.73 T

224 GB/s

5.68 T

224 GB/s

5.53 T

216 GB/s

5.53 T

218 GB/s

4.49 T

216 GB/s

4.49 T

216 GB/s

3.96 T

216 GB/s

3.89 T

160 GB/s

2.46 T

96 GB/s

2.06 T

94 GB/s

1.89 T

96 GB/s

1.86 T

81 GB/s

1.86 T

81 GB/s

1.66 T

96 GB/s

1.39 T

64 GB/s

1.31 T

81 GB/s

1.31 T

81 GB/s

1.25 T

48 GB/s

1.25 T

96 GB/s

1.02 T

81 GB/s