User | anthonynelzin |
Upload Date | September 19 2025 12:39 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | ARM |
System Information | |
---|---|
Operating System | iOS 26.0 |
Model | iPhone18,4 |
Model ID | iPhone18,4 |
Motherboard | D23AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.25 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 11.46 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2304
428.4 IPS |
|
Image Classification (HP)
|
100% |
14654
2.73 KIPS |
|
Image Classification (Q)
|
97% |
22418
4.18 KIPS |
|
Image Segmentation (SP)
|
100% |
2125
34.4 IPS |
|
Image Segmentation (HP)
|
100% |
19638
318.3 IPS |
|
Image Segmentation (Q)
|
99% |
25113
407.1 IPS |
|
Pose Estimation (SP)
|
100% |
9925
11.6 IPS |
|
Pose Estimation (HP)
|
100% |
152050
177.4 IPS |
|
Pose Estimation (Q)
|
95% |
297300
348.5 IPS |
|
Object Detection (SP)
|
100% |
2520
199.9 IPS |
|
Object Detection (HP)
|
100% |
17367
1.38 KIPS |
|
Object Detection (Q)
|
91% |
24215
1.93 KIPS |
|
Face Detection (SP)
|
100% |
4076
48.4 IPS |
|
Face Detection (HP)
|
100% |
40637
482.9 IPS |
|
Face Detection (Q)
|
100% |
56766
674.5 IPS |
|
Depth Estimation (SP)
|
100% |
8347
64.3 IPS |
|
Depth Estimation (HP)
|
99% |
104117
802.2 IPS |
|
Depth Estimation (Q)
|
85% |
164858
1.29 KIPS |
|
Style Transfer (SP)
|
100% |
23958
30.8 IPS |
|
Style Transfer (HP)
|
100% |
258652
332.5 IPS |
|
Style Transfer (Q)
|
96% |
350042
451.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5253
194.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
54674
2.02 KIPS |
|
Image Super-Resolution (Q)
|
99% |
82546
3.05 KIPS |
|
Text Classification (SP)
|
100% |
3569
4.76 KIPS |
|
Text Classification (HP)
|
99% |
6412
8.56 KIPS |
|
Text Classification (Q)
|
93% |
6398
8.59 KIPS |
|
Machine Translation (SP)
|
100% |
4765
82.1 IPS |
|
Machine Translation (HP)
|
100% |
9102
156.8 IPS |
|
Machine Translation (Q)
|
98% |
11804
204.0 IPS |