Gigabyte Technology Co., Ltd. TRX50 AI TOP
Geekbench AI Score
48302
Single Precision Score
72224
Half Precision Score
35122
Quantized Score
Geekbench AI 1.3.0 for Windows AVX2
Result Information
| Upload Date | June 14 2025 11:50 AM |
| Views | 3 |
System Information
| AI Information | |
|---|---|
| Framework | ONNX |
| Backend | DirectML |
| Device | NVIDIA GeForce RTX 5090 |
| System Information | |
|---|---|
| Operating System | Microsoft Windows 11 Pro (64-bit) |
| Model | Gigabyte Technology Co., Ltd. TRX50 AI TOP |
| Motherboard | Gigabyte Technology Co., Ltd. TRX50 AI TOP |
| Power Plan | Balanced |
| CPU Information | |
|---|---|
| Name | AMD Ryzen Threadripper 7970X 32-Cores |
| Topology | 1 Processor, 32 Cores, 64 Threads |
| Identifier | AuthenticAMD Family 25 Model 24 Stepping 1 |
| Base Frequency | 4.00 GHz |
| Cluster 1 | 32 Cores |
| Memory Information | |
|---|---|
| Size | 384.00 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
17330
3.22 KIPS |
|
|
Image Classification (HP)
|
100% |
22184
4.13 KIPS |
|
|
Image Classification (Q)
|
100% |
14603
2.72 KIPS |
|
|
Image Segmentation (SP)
|
100% |
38598
625.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
49587
803.8 IPS |
|
|
Image Segmentation (Q)
|
98% |
35351
574.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
403499
470.8 IPS |
|
|
Pose Estimation (HP)
|
100% |
948566
1.11 KIPS |
|
|
Pose Estimation (Q)
|
96% |
323522
379.0 IPS |
|
|
Object Detection (SP)
|
100% |
23960
1.90 KIPS |
|
|
Object Detection (HP)
|
100% |
31442
2.49 KIPS |
|
|
Object Detection (Q)
|
85% |
19782
1.59 KIPS |
|
|
Face Detection (SP)
|
100% |
73640
875.0 IPS |
|
|
Face Detection (HP)
|
100% |
99480
1.18 KIPS |
|
|
Face Detection (Q)
|
97% |
57958
691.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
106958
824.1 IPS |
|
|
Depth Estimation (HP)
|
99% |
193513
1.49 KIPS |
|
|
Depth Estimation (Q)
|
77% |
75279
603.0 IPS |
|
|
Style Transfer (SP)
|
100% |
605661
778.6 IPS |
|
|
Style Transfer (HP)
|
100% |
1734794
2.23 KIPS |
|
|
Style Transfer (Q)
|
98% |
504240
650.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
74010
2.73 KIPS |
|
|
Image Super-Resolution (HP)
|
100% |
97007
3.58 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
52938
1.96 KIPS |
|
|
Text Classification (SP)
|
100% |
4032
5.38 KIPS |
|
|
Text Classification (HP)
|
100% |
4866
6.50 KIPS |
|
|
Text Classification (Q)
|
97% |
2363
3.17 KIPS |
|
|
Machine Translation (SP)
|
100% |
7510
129.4 IPS |
|
|
Machine Translation (HP)
|
100% |
7468
128.6 IPS |
|
|
Machine Translation (Q)
|
70% |
3142
58.9 IPS |
