Geekbench AI Score

17660
Single Precision Score
24128
Half Precision Score
11752
Quantized Score
Geekbench AI 1.2.0 for Windows x86 (64-bit)

Result Information

User krofa
Upload Date March 02 2025 03:00 AM
Views 8
Notes qwen2.5-32b-q4 - 8K ctx

System Information

AI Information
Framework ONNX
Backend DirectML
Device NVIDIA RTX A6000
System Information
Operating System Microsoft Windows 10 Pro (64-bit)
Model Generic
Motherboard ASRock X79 Professional
Power PlanHigh performance
CPU Information
Name Intel Xeon E5-1680 v2
Topology 1 Processor, 8 Cores, 16 Threads
Identifier GenuineIntel Family 6 Model 62 Stepping 4
Base Frequency 3.80 GHz
Cluster 18 Cores
Memory Information
Size 32.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 7071
1.32 KIPS
 
Image Classification (HP)
99% 8852
1.65 KIPS
 
Image Classification (Q)
100% 5199
966.9 IPS
 
Image Segmentation (SP)
100% 8076
130.9 IPS
 
Image Segmentation (HP)
100% 9358
151.7 IPS
 
Image Segmentation (Q)
98% 6673
108.5 IPS
 
Pose Estimation (SP)
100% 155230
181.1 IPS
 
Pose Estimation (HP)
100% 279873
326.6 IPS
 
Pose Estimation (Q)
96% 115088
134.8 IPS
 
Object Detection (SP)
100% 9084
720.6 IPS
 
Object Detection (HP)
100% 11495
911.8 IPS
 
Object Detection (Q)
85% 6602
531.1 IPS
 
Face Detection (SP)
100% 18734
222.6 IPS
 
Face Detection (HP)
100% 23661
281.1 IPS
 
Face Detection (Q)
97% 14382
171.5 IPS
 
Depth Estimation (SP)
100% 54088
416.7 IPS
 
Depth Estimation (HP)
99% 83583
644.0 IPS
 
Depth Estimation (Q)
77% 33609
268.9 IPS
 
Style Transfer (SP)
100% 238612
306.7 IPS
 
Style Transfer (HP)
100% 496052
637.7 IPS
 
Style Transfer (Q)
98% 170990
220.5 IPS
 
Image Super-Resolution (SP)
100% 32324
1.19 KIPS
 
Image Super-Resolution (HP)
100% 44212
1.63 KIPS
 
Image Super-Resolution (Q)
99% 19043
705.1 IPS
 
Text Classification (SP)
100% 2146
2.86 KIPS
 
Text Classification (HP)
99% 2686
3.58 KIPS
 
Text Classification (Q)
97% 1120
1.50 KIPS
 
Machine Translation (SP)
100% 2185
37.6 IPS
 
Machine Translation (HP)
100% 2154
37.1 IPS
 
Machine Translation (Q)
70% 1082
20.3 IPS
 

Compare

Set Baseline Geekbench 6 now available