User | richh- |
Upload Date | September 14 2025 10:38 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 26.0 (Build 25A353) |
Model | MacBook Pro (16-inch, 2023) |
Model ID | Mac14,6 |
Motherboard | Mac14,6 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.68 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 96.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1351
251.2 IPS |
|
Image Classification (HP)
|
100% |
16125
3.00 KIPS |
|
Image Classification (Q)
|
96% |
18961
3.54 KIPS |
|
Image Segmentation (SP)
|
100% |
1673
27.1 IPS |
|
Image Segmentation (HP)
|
100% |
20348
329.9 IPS |
|
Image Segmentation (Q)
|
99% |
25161
407.9 IPS |
|
Pose Estimation (SP)
|
100% |
12145
14.2 IPS |
|
Pose Estimation (HP)
|
100% |
106636
124.4 IPS |
|
Pose Estimation (Q)
|
95% |
105421
123.6 IPS |
|
Object Detection (SP)
|
100% |
1630
129.3 IPS |
|
Object Detection (HP)
|
99% |
16464
1.31 KIPS |
|
Object Detection (Q)
|
91% |
18200
1.45 KIPS |
|
Face Detection (SP)
|
100% |
3618
43.0 IPS |
|
Face Detection (HP)
|
100% |
37035
440.1 IPS |
|
Face Detection (Q)
|
100% |
48097
571.5 IPS |
|
Depth Estimation (SP)
|
100% |
6089
46.9 IPS |
|
Depth Estimation (HP)
|
99% |
89307
688.1 IPS |
|
Depth Estimation (Q)
|
85% |
113687
888.4 IPS |
|
Style Transfer (SP)
|
100% |
25388
32.6 IPS |
|
Style Transfer (HP)
|
100% |
208604
268.2 IPS |
|
Style Transfer (Q)
|
96% |
192013
247.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4965
183.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
45752
1.69 KIPS |
|
Image Super-Resolution (Q)
|
99% |
52704
1.95 KIPS |
|
Text Classification (SP)
|
100% |
2472
3.30 KIPS |
|
Text Classification (HP)
|
99% |
4266
5.69 KIPS |
|
Text Classification (Q)
|
93% |
4304
5.78 KIPS |
|
Machine Translation (SP)
|
100% |
4388
75.6 IPS |
|
Machine Translation (HP)
|
100% |
4247
73.1 IPS |
|
Machine Translation (Q)
|
98% |
4409
76.2 IPS |