User | sfoskett |
Upload Date | December 10 2024 04:57 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B2082) |
Model | Mac mini (2024) |
Model ID | Mac16,11 |
Motherboard | Mac16,11 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.51 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2080
386.8 IPS |
|
Image Classification (HP)
|
100% |
17562
3.27 KIPS |
|
Image Classification (Q)
|
97% |
22361
4.17 KIPS |
|
Image Segmentation (SP)
|
100% |
2534
41.1 IPS |
|
Image Segmentation (HP)
|
100% |
23303
377.8 IPS |
|
Image Segmentation (Q)
|
99% |
32378
524.9 IPS |
|
Pose Estimation (SP)
|
100% |
18873
22.0 IPS |
|
Pose Estimation (HP)
|
100% |
123573
144.2 IPS |
|
Pose Estimation (Q)
|
95% |
232079
272.0 IPS |
|
Object Detection (SP)
|
100% |
2494
197.8 IPS |
|
Object Detection (HP)
|
100% |
20050
1.59 KIPS |
|
Object Detection (Q)
|
91% |
24343
1.95 KIPS |
|
Face Detection (SP)
|
100% |
4614
54.8 IPS |
|
Face Detection (HP)
|
100% |
45104
535.9 IPS |
|
Face Detection (Q)
|
100% |
64789
769.8 IPS |
|
Depth Estimation (SP)
|
100% |
8905
68.6 IPS |
|
Depth Estimation (HP)
|
99% |
111781
861.2 IPS |
|
Depth Estimation (Q)
|
85% |
179658
1.40 KIPS |
|
Style Transfer (SP)
|
100% |
35481
45.6 IPS |
|
Style Transfer (HP)
|
100% |
238550
306.7 IPS |
|
Style Transfer (Q)
|
96% |
305533
394.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
7042
260.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
46752
1.73 KIPS |
|
Image Super-Resolution (Q)
|
99% |
79977
2.95 KIPS |
|
Text Classification (SP)
|
100% |
2927
3.91 KIPS |
|
Text Classification (HP)
|
100% |
5079
6.78 KIPS |
|
Text Classification (Q)
|
93% |
5187
6.96 KIPS |
|
Machine Translation (SP)
|
100% |
5799
99.9 IPS |
|
Machine Translation (HP)
|
100% |
16127
277.8 IPS |
|
Machine Translation (Q)
|
98% |
16072
277.7 IPS |