User | jwchess |
Upload Date | January 29 2025 09:21 AM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.3 (Build 24D60) |
Model | MacBook Pro (14-inch, 2024) |
Model ID | Mac16,8 |
Motherboard | Mac16,8 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.49 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2087
388.2 IPS |
|
Image Classification (HP)
|
100% |
17660
3.28 KIPS |
|
Image Classification (Q)
|
97% |
23226
4.33 KIPS |
|
Image Segmentation (SP)
|
100% |
2457
39.8 IPS |
|
Image Segmentation (HP)
|
100% |
23161
375.5 IPS |
|
Image Segmentation (Q)
|
99% |
32487
526.6 IPS |
|
Pose Estimation (SP)
|
100% |
18812
22.0 IPS |
|
Pose Estimation (HP)
|
100% |
123419
144.0 IPS |
|
Pose Estimation (Q)
|
95% |
230163
269.8 IPS |
|
Object Detection (SP)
|
100% |
2448
194.2 IPS |
|
Object Detection (HP)
|
100% |
21447
1.70 KIPS |
|
Object Detection (Q)
|
91% |
24384
1.95 KIPS |
|
Face Detection (SP)
|
100% |
4508
53.6 IPS |
|
Face Detection (HP)
|
100% |
44557
529.4 IPS |
|
Face Detection (Q)
|
100% |
63440
753.8 IPS |
|
Depth Estimation (SP)
|
100% |
8801
67.8 IPS |
|
Depth Estimation (HP)
|
99% |
105350
811.7 IPS |
|
Depth Estimation (Q)
|
85% |
176418
1.38 KIPS |
|
Style Transfer (SP)
|
100% |
35269
45.3 IPS |
|
Style Transfer (HP)
|
100% |
233110
299.7 IPS |
|
Style Transfer (Q)
|
96% |
304008
392.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
7009
258.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
46367
1.71 KIPS |
|
Image Super-Resolution (Q)
|
99% |
77544
2.86 KIPS |
|
Text Classification (SP)
|
100% |
2918
3.89 KIPS |
|
Text Classification (HP)
|
100% |
5580
7.45 KIPS |
|
Text Classification (Q)
|
93% |
5316
7.14 KIPS |
|
Machine Translation (SP)
|
100% |
5749
99.0 IPS |
|
Machine Translation (HP)
|
100% |
17160
295.6 IPS |
|
Machine Translation (Q)
|
98% |
17052
294.7 IPS |