Upload Date | June 13 2025 01:22 PM |
Views | 4 |
System Information | |
---|---|
Operating System | iOS 16.7.2 |
Model | iPad Pro (11-inch, 4th generation) |
Model ID | iPad14,3 |
Motherboard | J617AP |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.49 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
L1 Instruction Cache | 128 KB x 1 |
L1 Data Cache | 64.0 KB x 1 |
L2 Cache | 4.00 MB x 1 |
Memory Information | |
---|---|
Size | 7.35 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
3498
654.5 IPS |
|
Image Classification (F16)
|
100% |
3439
643.5 IPS |
|
Image Classification (I8)
|
99% |
3437
643.2 IPS |
|
Image Segmentation (F32)
|
100% |
900
15.0 IPS |
|
Image Segmentation (F16)
|
100% |
866
14.5 IPS |
|
Image Segmentation (I8)
|
100% |
841
14.1 IPS |
|
Pose Estimation (F32)
|
100% |
23695
28.7 IPS |
|
Pose Estimation (F16)
|
100% |
25218
30.5 IPS |
|
Pose Estimation (I8)
|
100% |
25000
30.3 IPS |
|
Object Detection (F32)
|
100% |
3070
229.2 IPS |
|
Object Detection (F16)
|
100% |
3102
231.6 IPS |
|
Object Detection (I8)
|
97% |
3058
228.3 IPS |
|
Face Detection (F32)
|
100% |
9805
116.6 IPS |
|
Face Detection (F16)
|
97% |
11185
133.0 IPS |
|
Face Detection (I8)
|
96% |
11208
133.3 IPS |
|
Depth Estimation (F32)
|
100% |
16169
125.4 IPS |
|
Depth Estimation (F16)
|
100% |
17374
134.7 IPS |
|
Depth Estimation (I8)
|
99% |
17094
132.6 IPS |
|
Style Transfer (F32)
|
100% |
37743
49.6 IPS |
|
Style Transfer (F16)
|
100% |
43220
56.9 IPS |
|
Style Transfer (I8)
|
100% |
46764
61.5 IPS |
|
Image Super-Resolution (F32)
|
100% |
9294
331.9 IPS |
|
Image Super-Resolution (F16)
|
100% |
9864
352.3 IPS |
|
Image Super-Resolution (I8)
|
100% |
9877
352.8 IPS |
|
Text Classification (F32)
|
100% |
937
1.35 KIPS |
|
Text Classification (F16)
|
100% |
927
1.33 KIPS |
|
Text Classification (I8)
|
96% |
937
1.35 KIPS |
|
Machine Translation (F32)
|
100% |
1334
24.5 IPS |
|
Machine Translation (F16)
|
100% |
1389
25.6 IPS |
|
Machine Translation (I8)
|
99% |
1387
25.5 IPS |