Generic
Geekbench AI Score
2502
Single Precision Score
875
Half Precision Score
3873
Quantized Score
Geekbench AI 1.4.0 for Windows AVX2
Result Information
| Upload Date | July 03 2025 01:14 AM |
| Views | 4 |
System Information
| AI Information | |
|---|---|
| Framework | ONNX |
| Backend | CPU |
| Device | AMD Ryzen Threadripper 3990X |
| System Information | |
|---|---|
| Operating System | Microsoft Windows 11 Pro for Workstations (64-bit) |
| Model | Generic |
| Motherboard | ASRock TRX40 Creator |
| CPU Information | |
|---|---|
| Name | AMD Ryzen Threadripper 3990X |
| Topology | 1 Processor, 64 Cores, 128 Threads |
| Identifier | AuthenticAMD Family 23 Model 49 Stepping 0 |
| Base Frequency | 2.90 GHz |
| Cluster 1 | 32 Cores |
| Memory Information | |
|---|---|
| Size | 256.00 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1639
304.8 IPS |
|
|
Image Classification (HP)
|
100% |
362
67.4 IPS |
|
|
Image Classification (Q)
|
96% |
2678
500.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
1306
21.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
448
7.27 IPS |
|
|
Image Segmentation (Q)
|
97% |
6130
99.7 IPS |
|
|
Pose Estimation (SP)
|
100% |
14053
16.4 IPS |
|
|
Pose Estimation (HP)
|
100% |
4771
5.57 IPS |
|
|
Pose Estimation (Q)
|
86% |
20559
24.3 IPS |
|
|
Object Detection (SP)
|
100% |
1738
137.9 IPS |
|
|
Object Detection (HP)
|
100% |
447
35.5 IPS |
|
|
Object Detection (Q)
|
58% |
2338
255.5 IPS |
|
|
Face Detection (SP)
|
100% |
4536
53.9 IPS |
|
|
Face Detection (HP)
|
100% |
814
9.68 IPS |
|
|
Face Detection (Q)
|
96% |
6193
73.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
6756
52.1 IPS |
|
|
Depth Estimation (HP)
|
99% |
1200
9.24 IPS |
|
|
Depth Estimation (Q)
|
78% |
8442
67.4 IPS |
|
|
Style Transfer (SP)
|
100% |
19913
25.6 IPS |
|
|
Style Transfer (HP)
|
100% |
9042
11.6 IPS |
|
|
Style Transfer (Q)
|
87% |
20443
26.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1069
39.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
777
28.7 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
1762
65.3 IPS |
|
|
Text Classification (SP)
|
100% |
409
546.2 IPS |
|
|
Text Classification (HP)
|
100% |
303
404.2 IPS |
|
|
Text Classification (Q)
|
97% |
387
517.9 IPS |
|
|
Machine Translation (SP)
|
100% |
691
11.9 IPS |
|
|
Machine Translation (HP)
|
100% |
370
6.37 IPS |
|
|
Machine Translation (Q)
|
68% |
1322
25.5 IPS |
