iPad (8th generation)
Geekbench AI Score
457
Single Precision Score
2010
Half Precision Score
695
Quantized Score
Geekbench AI 1.0.0 for iOS AArch64
Result Information
| User | Angus72 |
| Upload Date | August 31 2024 10:43 AM |
| Views | 5 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPad (8th generation) |
| Model ID | iPad11,6 |
| Motherboard | J171aAP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 2.88 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
269
50.0 IPS |
|
|
Image Classification (HP)
|
100% |
2055
382.2 IPS |
|
|
Image Classification (Q)
|
99% |
2072
386.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
239
3.88 IPS |
|
|
Image Segmentation (HP)
|
100% |
387
6.28 IPS |
|
|
Image Segmentation (Q)
|
100% |
384
6.22 IPS |
|
|
Pose Estimation (SP)
|
100% |
938
1.09 IPS |
|
|
Pose Estimation (HP)
|
100% |
22568
26.3 IPS |
|
|
Pose Estimation (Q)
|
94% |
675
0.79 IPS |
|
|
Object Detection (SP)
|
100% |
243
19.3 IPS |
|
|
Object Detection (HP)
|
100% |
1379
109.4 IPS |
|
|
Object Detection (Q)
|
94% |
189
15.1 IPS |
|
|
Face Detection (SP)
|
100% |
571
6.79 IPS |
|
|
Face Detection (HP)
|
100% |
5254
62.4 IPS |
|
|
Face Detection (Q)
|
100% |
240
2.86 IPS |
|
|
Depth Estimation (SP)
|
100% |
587
4.52 IPS |
|
|
Depth Estimation (HP)
|
99% |
18539
142.8 IPS |
|
|
Depth Estimation (Q)
|
97% |
18621
144.0 IPS |
|
|
Style Transfer (SP)
|
100% |
1615
2.08 IPS |
|
|
Style Transfer (HP)
|
100% |
1573
2.02 IPS |
|
|
Style Transfer (Q)
|
100% |
1601
2.06 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
482
17.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3438
126.9 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
457
16.9 IPS |
|
|
Text Classification (SP)
|
100% |
265
353.3 IPS |
|
|
Text Classification (HP)
|
100% |
294
392.9 IPS |
|
|
Text Classification (Q)
|
93% |
292
391.5 IPS |
|
|
Machine Translation (SP)
|
100% |
398
6.85 IPS |
|
|
Machine Translation (HP)
|
100% |
282
4.86 IPS |
|
|
Machine Translation (Q)
|
98% |
275
4.76 IPS |
