Performance Data for Consumer Edge Use Cases
Self-Checkout Use Cases
Find the latest performance data by choice of Intel® processors for the vision-enabled workloads that drive self-checkout.
Detection and Classification
Pipeline: Product identification with tracking
Mode: Power save
| Platform Name | CPU | Device | Model | Video Type/Resolution | Presicion | Cumulative Throughput* | Number of Streams** | Latency*** | Batch Size | Average Package Power (Watts) |
|---|---|---|---|---|---|---|---|---|---|---|
| Raptor Lake (Gen 13) | U300L | GPU | detection - yolov11n classification - efficientnet-b0 |
RTSP Camera (AVC 1920x1080 @15FPS) |
INT8 | 45.09 | 3 | 116.497 | 1 | 9.72 |
| Raptor Lake (Gen 13) | Core 3-100HL | GPU | detection - yolov11n classification - efficientnet-b0 |
RTSP Camera (AVC 1920x1080 @15FPS) |
INT8 | 60.24 | 4 | 155.555 | 1 | 23.55 |
| Raptor Lake (Gen 13) | Core 5-120HL | GPU | detection - yolov11n classification - efficientnet-b0 |
RTSP Camera (AVC 1920x1080 @15FPS) |
INT8 | 104.78 | 7 | 125.582 | 1 | 34.61 |
| Raptor Lake Refresh(Gen 14) | Processor 300 | GPU | detection - yolov11n classification - efficientnet-b0 |
RTSP Camera (AVC 1920x1080 @15FPS) |
INT8 | 45.15 | 3 | 219.974 | 1 | 17.71 |
| Meteor Lake (Gen 14) | i5-14500 | GPU | detection - yolov11n classification - efficientnet-b0 |
RTSP Camera (AVC 1920x1080 @15FPS) |
INT8 | 44.95 | 3 | 107.528 | 1 | 22.81 |
| Meteor Lake (Gen 14) | Ultra 5 125HL | GPU:NPU | detection - yolov11n classification - efficientnet-b0 |
RTSP Camera (AVC 3840x2160 @15FPS) |
INT8 | 194.72 | 13 | 156.517 | gpu:1,npu:1 | 12.32 |
| Meteor Lake (Gen 14) | Ultra 5 125HL | GPU:NPU | detection - yolov11n classification - efficientnet-b0 |
RTSP Camera (AVC 1920x1080 @15FPS) |
INT8 | 210.05 | 14 | 157.366 | gpu:1,npu:1 | 40.03 |
| Meteor Lake (Gen 14) | Ultra 5 125HL | GPU | detection - yolov11n classification - efficientnet-b0 |
RTSP Camera (AVC 1920x1080 @15FPS) |
INT8 | 150.02 | 10 | 130.962 | 1 | 37.37 |
| Meteor Lake (Gen 14) | Ultra 5 125HL | NPU | detection - yolov11n classification - efficientnet-b0 |
RTSP Camera (AVC 1920x1080 @15FPS) |
INT8 | 104.97 | 7 | 112.687 | 1 | 13.52 |
Full pipeline
Pipeline: Product identification with tracking and age verification
Mode: Power save
| Platform Name | CPU | Device | Model | Video Type/Resolution | Presicion | Cumulative Throughput* | Num of Streams** | Latency*** | Batch Size | Average Package Power (Watts) |
|---|---|---|---|---|---|---|---|---|---|---|
| Raptor Lake (Gen 13) | U300L | GPU | detection - yolov11n classification - efficientnet-b0 face-detection-retail-0004 age-gender-recognition-retail-0013 |
RTSP Camera (AVC 1920x1080 @15FPS) |
INT8 INT8 FP16 FP16 |
64.11 | 4 | 485.672 | 1 | 14.99 |
| Raptor Lake (Gen 13) | Core 3-100HL | GPU | detection - yolov11n classification - efficientnet-b0 face-detection-retail-0004 age-gender-recognition-retail-0013 |
RTSP Camera (AVC 1920x1080 @15FPS) |
INT8 INT8 FP16 FP16 |
76.14 | 5 | 499.858 | 1 | 38.72 |
| Raptor Lake (Gen 13) | Core 5-120HL | GPU | detection - yolov11n classification - efficientnet- face-detection-retail-0004 age-gender-recognition-retail-0013 |
RTSP Camera (AVC 1920x1080 @15FPS) |
INT8 INT8 FP16 FP16 |
108.94 | 7 | 526.228 | 1 | 44.51 |
| Raptor Lake Refresh(Gen 14) | Processor 300 | GPU | detection - yolov11n classification - efficientnet-b0 face-detection-retail-0004 age-gender-recognition-retail-0013 |
RTSP Camera (AVC 1920x1080 @15FPS) |
INT8 INT8 FP16 FP16 |
35.27 | 2 | 404.198 | 1 | 20.58 |
| Raptor Lake Refresh(Gen 14) | i5-14500 | GPU | detection - yolov11n classification - efficientnet-b0 face-detection-retail-0004 age-gender-recognition-retail-0013 |
RTSP Camera (AVC 1920x1080 @15FPS) |
INT8 INT8 FP16 FP16 |
76.76 | 5 | 531.545 | 1 | 50.02 |
| Meteor Lake (Gen 14) | Ultra 5 125HL | GPU:NPU | detection - yolov11n classification - efficientnet-b0 face-detection-retail-0004 age-gender-recognition-retail-0013 |
RTSP Camera (AVC 1920x1080 @15FPS) |
INT8 INT8 FP16 FP16 |
165.7 | 10 | 467.816 | gpu:1,npu:1 | 43.55 |
| Meteor Lake (Gen 14) | Ultra 5 125HL | GPU | detection - yolov11n classification - efficientnet-b0 face-detection-retail-0004 age-gender-recognition-retail-0013 |
RTSP Camera (AVC 1920x1080 @15FPS) |
INT8 INT8 FP16 FP16 |
150.25 | 9 | 465.043 | 1 | 44.72 |
| Meteor Lake (Gen 14) | Ultra 5 125HL | NPU | detection - yolov11n classification - efficientnet-b0 face-detection-retail-0004 age-gender-recognition-retail-0013 |
RTSP Camera (AVC 1920x1080 @15FPS) |
INT8 INT8 FP16 FP16 |
80.09 | 5 | 532.48 | 1 | 15.77 |
*MTL data is based on preliminary analysis, and we expect a performance boost after further optimization
You can run the performance benchmarks using existing models or your own models.
Hardware and software configuration (measured Dec 19, 2025):
Hardware configuration for 1-node, Intel Corporation Alder Lake Client Platform, 1x Intel(R) Processor U300L, 5 cores, 200W TDP, HT ?, Turbo On, Total Memory 64GB (2x32GB DDR5 5600MT/s [5200MT/s]), BIOS Intel(R) Processor U300L, microcode 0x4128, 1x Ethernet Connection, 1x AX88179 Gigabit Ethernet, 1x , 1x 931.5G Samsung SSD 970 EVO Plus 1TB, Ubuntu 24.04.1 LTS, 6.14.0-34-generic. Test by Intel.
Hardware configuration for 1-node, Intel Corporation Alder Lake Client Platform, 1x Intel(R) Core(TM) 3 100HL, 8 cores, 200W TDP, HT ?, Turbo On, Total Memory 64GB (2x32GB DDR5 5600MT/s [5200MT/s]), BIOS Intel(R) Core(TM) 3 100HL, microcode 0x4123, 1x Ethernet Connection, 1x AX88179 Gigabit Ethernet, 3x , 1x 114.6G SanDisk 3.2Gen1, 1x 232.9G WD_BLACK SN770 250GB, Ubuntu 24.04.1 LTS, 6.6-intel. Test by Intel.
Hardware configuration for 1-node, Intel Corporation Alder Lake Client Platform, 1x Intel(R) Core(TM) 5 120HL, 12 cores, 200W TDP, HT ?, Turbo On, Total Memory 64GB (2x32GB DDR5 5600MT/s [5200MT/s]), BIOS Intel(R) Core(TM) 5 120HL, microcode 0x4123, 3x , 1x Ethernet Connection, 1x AX88179 Gigabit Ethernet, 1x 114.6G SanDisk 3.2Gen1, 1x 232.9G WD_BLACK SN770 250GB, Ubuntu 22.04.4 LTS, 6.6-intel. Test by Intel
Hardware configuration for 1-node, Intel Corporation Raptor Lake Client Platform, 1x Intel(R) 300, 2 cores, 46W TDP, HT ?, Turbo Off, Total Memory 64GB (2x32GB DDR5 4800MT/s [4800MT/s]), BIOS Intel(R) 300, microcode 0x3a, 1x , 1x Ethernet Connection, 1x 114.6G SanDisk 3.2Gen1, 1x 931.5G Samsung SSD 970 EVO Plus 1TB, Ubuntu 24.04 LTS, 6.14.0-33-generic. Test by Intel
Hardware configuration for 1-node, Intel Corporation Raptor Lake Client Platform, 1x Intel(R) Core(TM) i5-14500, 14 cores, 65W TDP, HT ?, Turbo On, Total Memory 64GB (2x32GB DDR5 4800MT/s [4800MT/s]), BIOS Intel(R) Core(TM) i5-14500, microcode 0x3a, 1x , 1x Ethernet Connection, 1x 114.6G SanDisk 3.2Gen1, 1x 931.5G Samsung SSD 970 EVO Plus 1TB, Ubuntu 24.04 LTS, 6.14.0-35-generic. Test by Intel as of Thu Nov 13 02:31:08 PM IST 2025.
Hardware configuration for 1-node, Intel Corporation Meteor Lake Client Platform, 1x Intel(R) Core(TM) Ultra 5 125HL, 14 cores, 45W TDP, HT On, Turbo On, Total Memory 64GB (2x32GB DDR5 5600MT/s [5600MT/s]), BIOS Intel(R) Core(TM) Ultra 5 125HL, microcode 0x24, 2x Unknown NIC, 1x AX88179 Gigabit Ethernet, 1x 232.9G WD_BLACK SN770 250GB, Ubuntu 24.04.3 LTS, 6.14.0-27-generic
- Wall power refers to platform power consumption.
- Accuracy (if listed) was validated with the specified dataset.