User | fp32 |
Upload Date | January 24 2025 04:42 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B2091) |
Model | Mac mini (2024) |
Model ID | Mac16,11 |
Motherboard | Mac16,11 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.50 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2082
387.1 IPS |
|
Image Classification (HP)
|
100% |
18499
3.44 KIPS |
|
Image Classification (Q)
|
97% |
24469
4.57 KIPS |
|
Image Segmentation (SP)
|
100% |
2441
39.6 IPS |
|
Image Segmentation (HP)
|
100% |
23111
374.6 IPS |
|
Image Segmentation (Q)
|
99% |
32043
519.4 IPS |
|
Pose Estimation (SP)
|
100% |
18850
22.0 IPS |
|
Pose Estimation (HP)
|
100% |
123536
144.1 IPS |
|
Pose Estimation (Q)
|
95% |
230269
269.9 IPS |
|
Object Detection (SP)
|
100% |
2480
196.7 IPS |
|
Object Detection (HP)
|
100% |
20013
1.59 KIPS |
|
Object Detection (Q)
|
91% |
26058
2.08 KIPS |
|
Face Detection (SP)
|
100% |
4481
53.2 IPS |
|
Face Detection (HP)
|
100% |
44779
532.1 IPS |
|
Face Detection (Q)
|
100% |
64329
764.4 IPS |
|
Depth Estimation (SP)
|
100% |
8832
68.0 IPS |
|
Depth Estimation (HP)
|
99% |
110953
854.8 IPS |
|
Depth Estimation (Q)
|
85% |
183725
1.44 KIPS |
|
Style Transfer (SP)
|
100% |
35657
45.8 IPS |
|
Style Transfer (HP)
|
100% |
238736
306.9 IPS |
|
Style Transfer (Q)
|
96% |
305806
394.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
7018
259.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
48009
1.77 KIPS |
|
Image Super-Resolution (Q)
|
99% |
81082
2.99 KIPS |
|
Text Classification (SP)
|
100% |
2927
3.91 KIPS |
|
Text Classification (HP)
|
100% |
5694
7.60 KIPS |
|
Text Classification (Q)
|
93% |
5612
7.53 KIPS |
|
Machine Translation (SP)
|
100% |
5781
99.6 IPS |
|
Machine Translation (HP)
|
100% |
16413
282.7 IPS |
|
Machine Translation (Q)
|
98% |
16944
292.8 IPS |