Gigabyte Technology Co., Ltd. TRX40 AORUS XTREME
Geekbench AI Score
29032
Single Precision Score
31423
Half Precision Score
22514
Quantized Score
Geekbench AI 1.3.0 for Windows AVX2
Result Information
| User | danm1988 |
| Upload Date | March 31 2025 11:08 PM |
| Views | 5 |
System Information
| AI Information | |
|---|---|
| Framework | ONNX |
| Backend | DirectML |
| Device | AMD Radeon RX 6950 XT |
| System Information | |
|---|---|
| Operating System | Microsoft Windows 11 Pro for Workstations (64-bit) |
| Model | Gigabyte Technology Co., Ltd. TRX40 AORUS XTREME |
| Motherboard | Gigabyte Technology Co., Ltd. TRX40 AORUS XTREME |
| Power Plan | Ultimate Performance |
| CPU Information | |
|---|---|
| Name | AMD Ryzen Threadripper 3970X |
| Topology | 1 Processor, 32 Cores, 64 Threads |
| Identifier | AuthenticAMD Family 23 Model 49 Stepping 0 |
| Base Frequency | 3.70 GHz |
| Cluster 1 | 32 Cores |
| Memory Information | |
|---|---|
| Size | 256.00 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
12180
2.27 KIPS |
|
|
Image Classification (HP)
|
100% |
12012
2.23 KIPS |
|
|
Image Classification (Q)
|
99% |
9876
1.84 KIPS |
|
|
Image Segmentation (SP)
|
100% |
20789
337.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
16860
273.3 IPS |
|
|
Image Segmentation (Q)
|
98% |
17109
278.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
201356
234.9 IPS |
|
|
Pose Estimation (HP)
|
100% |
304175
354.9 IPS |
|
|
Pose Estimation (Q)
|
96% |
170234
199.5 IPS |
|
|
Object Detection (SP)
|
100% |
12423
985.4 IPS |
|
|
Object Detection (HP)
|
100% |
12734
1.01 KIPS |
|
|
Object Detection (Q)
|
87% |
10442
838.6 IPS |
|
|
Face Detection (SP)
|
100% |
38186
453.7 IPS |
|
|
Face Detection (HP)
|
100% |
40755
484.3 IPS |
|
|
Face Detection (Q)
|
97% |
30979
369.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
71993
554.7 IPS |
|
|
Depth Estimation (HP)
|
99% |
77249
595.2 IPS |
|
|
Depth Estimation (Q)
|
76% |
53998
433.6 IPS |
|
|
Style Transfer (SP)
|
100% |
346042
444.8 IPS |
|
|
Style Transfer (HP)
|
100% |
455935
586.1 IPS |
|
|
Style Transfer (Q)
|
98% |
277935
358.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
39751
1.47 KIPS |
|
|
Image Super-Resolution (HP)
|
100% |
45476
1.68 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
29564
1.09 KIPS |
|
|
Text Classification (SP)
|
100% |
3129
4.18 KIPS |
|
|
Text Classification (HP)
|
100% |
3160
4.22 KIPS |
|
|
Text Classification (Q)
|
97% |
2541
3.40 KIPS |
|
|
Machine Translation (SP)
|
100% |
5676
97.8 IPS |
|
|
Machine Translation (HP)
|
100% |
5801
99.9 IPS |
|
|
Machine Translation (Q)
|
70% |
3190
59.8 IPS |
