object detection benchmarks on edge AI hardware
Each table compares only results with the same model-size class and batch size. Search this workload · JSON.
Fastest in the best-covered like-for-like group (nano (YOLO-n), batch 1): Hailo-8 (M.2/PCIe, x86 host) at 1036 FPS D undated. 15 groups, 61 platforms.
Show data — 15 like-for-like tables
nano (YOLO-n) · batch 1 (16 platforms)
✓ Like-for-like: model-size class nano (YOLO-n), batch 1. Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Hailo-8 (M.2/PCIe, x86 host) | 1036 FPS throughput · b=1 | yolov8n INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · nano (YOLO-n) | D | 2.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8) undated |
| NVIDIA DGX Spark | 990 FPS inference_time · b=1 | YOLO11n FP16 · Ultralytics TensorRT · nano (YOLO-n) | B | 153 W spec platform spec envelope (not measured with this result) | Ultralytics docs benchmark table undated |
| NVIDIA Jetson AGX Thor | 719 FPS inference_time · b=1 | YOLO26n FP16 · Ultralytics TensorRT · nano (YOLO-n) | B | 130 W spec platform spec envelope (not measured with this result) | Ultralytics docs benchmark table undated |
| AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S) | 476 FPS inference_time · b=1 | YOLO26n FP32 · Ultralytics 8.4.165 ONNX Runtime MIGraphX EP · nano (YOLO-n) | B | 120 W spec platform spec envelope (not measured with this result) | Ultralytics docs: AMD ROCm/MIGraphX integration benchmark 2026 (year only) |
| NVIDIA Jetson AGX Orin 64GB | 435 FPS inference_time · b=1 | YOLO26n INT8 · Ultralytics TensorRT · nano (YOLO-n) | B | 65.00 W spec platform spec envelope (not measured with this result) | Ultralytics docs benchmark table undated |
| Hailo-10H (M.2/PCIe, x86 host) | 375 FPS throughput · b=1 | yolov8n INT8 (Hailo quantized) · Hailo DFC v5.4.0 / HailoRT (model zoo) · nano (YOLO-n) | D | 2.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-10H) undated |
| Apple M4 (10-core GPU, 120 GB/s) | 357 FPS latency_e2e · b=1 | YOLO26n FP16 · Ultralytics 8.4.168 Core AI (coreai-torch 0.4.3), macOS 27.0 · nano (YOLO-n) | B | unknown power n/a no power published | Ultralytics docs: Apple Core AI integration benchmark 2026 (year only) |
| Intel Core Ultra 7 258V (Lunar Lake) | 300 FPS inference_time · b=1 | YOLO26n FP32 · Ultralytics + OpenVINO 2026.2.1 · nano (YOLO-n) | C | unknown power n/a no power published | Ultralytics docs: Intel OpenVINO integration benchmark 2026 (year only) |
| NVIDIA Jetson Orin NX 16GB | 287 FPS inference_time · b=1 | YOLO26n INT8 · Ultralytics TensorRT · nano (YOLO-n) | B | unknown power n/a no power published | Ultralytics docs benchmark table undated |
| NVIDIA Jetson Orin Nano Super | 263 FPS inference_time · b=1 | YOLO26n INT8 · Ultralytics TensorRT · nano (YOLO-n) | B | 25.00 W spec reported in result source — spec | Ultralytics docs benchmark table undated |
| Intel Core Ultra X7 358H (Panther Lake) | 248 FPS inference_time · b=1 | YOLO26n FP16 · Ultralytics + OpenVINO 2026.2.1 · nano (YOLO-n) | C | unknown power n/a no power published | Ultralytics docs: Intel OpenVINO integration benchmark 2026 (year only) |
| Hailo-8L (M.2/PCIe, x86 host) | 201 FPS throughput · b=1 | yolov8n INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · nano (YOLO-n) | D | 1.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8L) undated |
| Intel Core Ultra 7 155H (Meteor Lake) | 173 FPS inference_time · b=1 | YOLO26n INT8 · Ultralytics + OpenVINO 2026.2.1 · nano (YOLO-n) | C | unknown power n/a no power published | Ultralytics docs: Intel OpenVINO integration benchmark 2026 (year only) |
| Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox) | 66.21 FPS inference_time · b=1 | yolov5n_512x288 INT8 (VNNX) · VectorBlox SDK (VNNX), no compression · nano (YOLO-n) | D | unknown power n/a no power published | Microchip VectorBlox SDK tutorial metrics undated |
| Raspberry Pi 5 + AI HAT+ (Hailo-8) | 46.08 FPS inference_time · b=1 | YOLO26n INT8 · Ultralytics Hailo HEF / HailoRT · nano (YOLO-n) | B | unknown power n/a no power published | Ultralytics docs: Hailo integration benchmark 2026 (year only) |
| Raspberry Pi 5 (CPU only) CPU-only | 14.92 FPS inference_time · b=1 | YOLO26n FP32/default · Ultralytics NCNN · nano (YOLO-n) | B | unknown power n/a no power published | Ultralytics docs benchmark table undated |
small (YOLO-s) · batch 1 (8 platforms)
✓ Like-for-like: model-size class small (YOLO-s), batch 1. Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Hailo-8 (M.2/PCIe, x86 host) | 633 FPS throughput · b=1 | yolov5s_wo_spp INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · small (YOLO-s) | D | 2.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8) undated |
| Hailo-10H (M.2/PCIe, x86 host) | 261 FPS throughput · b=1 | yolov5s_wo_spp INT8 (Hailo quantized) · Hailo DFC v5.4.0 / HailoRT (model zoo) · small (YOLO-s) | D | 2.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-10H) undated |
| Intel Core Ultra 7 258V (Lunar Lake) | 251 FPS inference_time · b=1 | YOLO26s INT8 · Ultralytics + OpenVINO 2026.2.1 · small (YOLO-s) | C | unknown power n/a no power published | Ultralytics docs: Intel OpenVINO integration benchmark 2026 (year only) |
| Intel Core Ultra X7 358H (Panther Lake) | 224 FPS inference_time · b=1 | YOLO26s INT8 · Ultralytics + OpenVINO 2026.2.1 · small (YOLO-s) | C | unknown power n/a no power published | Ultralytics docs: Intel OpenVINO integration benchmark 2026 (year only) |
| AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S) | 213 FPS inference_time · b=1 | YOLO26s FP32 · Ultralytics 8.4.165 ONNX Runtime MIGraphX EP · small (YOLO-s) | B | 120 W spec platform spec envelope (not measured with this result) | Ultralytics docs: AMD ROCm/MIGraphX integration benchmark 2026 (year only) |
| Hailo-8L (M.2/PCIe, x86 host) | 137 FPS throughput · b=1 | yolov5s_wo_spp INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · small (YOLO-s) | D | 1.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8L) undated |
| Intel Core Ultra 7 155H (Meteor Lake) | 108 FPS inference_time · b=1 | YOLO26s INT8 · Ultralytics + OpenVINO 2026.2.1 · small (YOLO-s) | C | unknown power n/a no power published | Ultralytics docs: Intel OpenVINO integration benchmark 2026 (year only) |
| Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox) | 30.35 FPS inference_time · b=1 | yolov9s_70s_15p_512x288 INT8 (VNNX) · VectorBlox SDK (VNNX), unstructured compression · small (YOLO-s) | D | unknown power n/a no power published | Microchip VectorBlox SDK tutorial metrics undated |
medium (YOLO-m) · batch 1 (8 platforms)
✓ Like-for-like: model-size class medium (YOLO-m), batch 1. Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Hailo-8 (M.2/PCIe, x86 host) | 242 FPS throughput · b=1 | yolov5m_wo_spp INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · medium (YOLO-m) | D | 2.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8) undated |
| Intel Core Ultra X7 358H (Panther Lake) | 178 FPS inference_time · b=1 | YOLO26m INT8 · Ultralytics + OpenVINO 2026.2.1 · medium (YOLO-m) | C | unknown power n/a no power published | Ultralytics docs: Intel OpenVINO integration benchmark 2026 (year only) |
| Intel Core Ultra 7 258V (Lunar Lake) | 175 FPS inference_time · b=1 | YOLO26m INT8 · Ultralytics + OpenVINO 2026.2.1 · medium (YOLO-m) | C | unknown power n/a no power published | Ultralytics docs: Intel OpenVINO integration benchmark 2026 (year only) |
| Hailo-10H (M.2/PCIe, x86 host) | 122 FPS throughput · b=1 | yolov5m_wo_spp INT8 (Hailo quantized) · Hailo DFC v5.4.0 / HailoRT (model zoo) · medium (YOLO-m) | D | 2.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-10H) undated |
| AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S) | 91.74 FPS inference_time · b=1 | YOLO26m FP32 · Ultralytics 8.4.165 ONNX Runtime MIGraphX EP · medium (YOLO-m) | B | 120 W spec platform spec envelope (not measured with this result) | Ultralytics docs: AMD ROCm/MIGraphX integration benchmark 2026 (year only) |
| Intel Core Ultra 7 155H (Meteor Lake) | 64.68 FPS inference_time · b=1 | YOLO26m INT8 · Ultralytics + OpenVINO 2026.2.1 · medium (YOLO-m) | C | unknown power n/a no power published | Ultralytics docs: Intel OpenVINO integration benchmark 2026 (year only) |
| Hailo-8L (M.2/PCIe, x86 host) | 62.90 FPS throughput · b=1 | yolov5m_wo_spp INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · medium (YOLO-m) | D | 1.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8L) undated |
| Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox) | 6.02 FPS inference_time · b=1 | yolov5m.relu INT8 (VNNX) · VectorBlox SDK (VNNX), no compression · medium (YOLO-m) | D | unknown power n/a no power published | Microchip VectorBlox SDK tutorial metrics undated |
medium (YOLO-m) · batch 8 (4 platforms)
✓ Like-for-like: model-size class medium (YOLO-m), batch 8. Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Hailo-8 (M.2/PCIe, x86 host) | 242 FPS throughput · b=8 | yolov5m_wo_spp INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · medium (YOLO-m) | D | 2.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8) undated |
| Hailo-10H (M.2/PCIe, x86 host) | 208 FPS throughput · b=8 | yolov5m_wo_spp INT8 (Hailo quantized) · Hailo DFC v5.4.0 / HailoRT (model zoo) · medium (YOLO-m) | D | 2.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-10H) undated |
| Hailo-8L (M.2/PCIe, x86 host) | 105 FPS throughput · b=8 | yolov5m INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · medium (YOLO-m) | D | 1.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8L) undated |
| Raspberry Pi 5 + AI HAT+ (Hailo-8) | 76.99 FPS FPS per stream, 1 stream(s) · b=8 | yolov8m INT8 · Hailo TAPPAS multi_stream_detection, HailoRT 4.19 · medium (YOLO-m) | C | unknown power n/a no power published | Seeed Studio wiki: multistream inference on RPi5 + Hailo-8 2025-12 (updated) |
large (YOLO-l) · batch 1 (4 platforms)
✓ Like-for-like: model-size class large (YOLO-l), batch 1. Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Intel Core Ultra X7 358H (Panther Lake) | 160 FPS inference_time · b=1 | YOLO26l INT8 · Ultralytics + OpenVINO 2026.2.1 · large (YOLO-l) | C | unknown power n/a no power published | Ultralytics docs: Intel OpenVINO integration benchmark 2026 (year only) |
| Intel Core Ultra 7 258V (Lunar Lake) | 134 FPS inference_time · b=1 | YOLO26l INT8 · Ultralytics + OpenVINO 2026.2.1 · large (YOLO-l) | C | unknown power n/a no power published | Ultralytics docs: Intel OpenVINO integration benchmark 2026 (year only) |
| AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S) | 66.67 FPS inference_time · b=1 | YOLO26l FP32 · Ultralytics 8.4.165 ONNX Runtime MIGraphX EP · large (YOLO-l) | B | 120 W spec platform spec envelope (not measured with this result) | Ultralytics docs: AMD ROCm/MIGraphX integration benchmark 2026 (year only) |
| Intel Core Ultra 7 155H (Meteor Lake) | 50.71 FPS inference_time · b=1 | YOLO26l INT8 · Ultralytics + OpenVINO 2026.2.1 · large (YOLO-l) | C | unknown power n/a no power published | Ultralytics docs: Intel OpenVINO integration benchmark 2026 (year only) |
xlarge (YOLO-x) · batch 1 (4 platforms)
✓ Like-for-like: model-size class xlarge (YOLO-x), batch 1. Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Intel Core Ultra X7 358H (Panther Lake) | 114 FPS inference_time · b=1 | YOLO26x INT8 · Ultralytics + OpenVINO 2026.2.1 · xlarge (YOLO-x) | C | unknown power n/a no power published | Ultralytics docs: Intel OpenVINO integration benchmark 2026 (year only) |
| Intel Core Ultra 7 258V (Lunar Lake) | 73.05 FPS inference_time · b=1 | YOLO26x INT8 · Ultralytics + OpenVINO 2026.2.1 · xlarge (YOLO-x) | C | unknown power n/a no power published | Ultralytics docs: Intel OpenVINO integration benchmark 2026 (year only) |
| AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S) | 36.90 FPS inference_time · b=1 | YOLO26x FP32 · Ultralytics 8.4.165 ONNX Runtime MIGraphX EP · xlarge (YOLO-x) | B | 120 W spec platform spec envelope (not measured with this result) | Ultralytics docs: AMD ROCm/MIGraphX integration benchmark 2026 (year only) |
| Intel Core Ultra 7 155H (Meteor Lake) | 28.85 FPS inference_time · b=1 | YOLO26x INT8 · Ultralytics + OpenVINO 2026.2.1 · xlarge (YOLO-x) | C | unknown power n/a no power published | Ultralytics docs: Intel OpenVINO integration benchmark 2026 (year only) |
nano (YOLO-n) · batch 8 (3 platforms)
✓ Like-for-like: model-size class nano (YOLO-n), batch 8. Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Hailo-8 (M.2/PCIe, x86 host) | 1036 FPS throughput · b=8 | yolov8n INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · nano (YOLO-n) | D | 2.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8) undated |
| Hailo-8L (M.2/PCIe, x86 host) | 437 FPS throughput · b=8 | yolov8n INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · nano (YOLO-n) | D | 1.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8L) undated |
| Hailo-10H (M.2/PCIe, x86 host) | 370 FPS throughput · b=8 | yolov8n INT8 (Hailo quantized) · Hailo DFC v5.4.0 / HailoRT (model zoo) · nano (YOLO-n) | D | 2.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-10H) undated |
small (YOLO-s) · batch 8 (3 platforms)
✓ Like-for-like: model-size class small (YOLO-s), batch 8. Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Hailo-8 (M.2/PCIe, x86 host) | 633 FPS throughput · b=8 | yolov5s_wo_spp INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · small (YOLO-s) | D | 2.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8) undated |
| Hailo-10H (M.2/PCIe, x86 host) | 370 FPS throughput · b=8 | yolov5s_wo_spp INT8 (Hailo quantized) · Hailo DFC v5.4.0 / HailoRT (model zoo) · small (YOLO-s) | D | 2.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-10H) undated |
| Hailo-8L (M.2/PCIe, x86 host) | 275 FPS throughput · b=8 | yolov5s_wo_spp INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · small (YOLO-s) | D | 1.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8L) undated |
mobile-class CNN · batch 1 (1 platforms)
✓ Like-for-like: model-size class mobile-class CNN, batch 1. Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox) | 25.81 FPS inference_time · b=1 | torchvision_ssdlite320_mobilenet_v3_large INT8 (VNNX) · VectorBlox SDK (VNNX), no compression · mobile-class CNN | D | unknown power n/a no power published | Microchip VectorBlox SDK tutorial metrics undated |
mid-size CNN · batch unknown (34 platforms)
✓ Like-for-like: model-size class mid-size CNN, batch unknown (size or batch not stated by source — unverified). Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Intel Xeon Platinum 6972P CPU-only | 969 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Xeon Platinum 8580 CPU-only | 516 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Xeon Platinum 8480+ CPU-only | 427 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| NVIDIA Jetson AGX Orin 64GB | 149 FPS throughput_offline · b=unknown | MLPerf Retinanet INT8/FP16 (MLPerf closed) · TensorRT (MLPerf Inference, older round) · mid-size CNN | D | 65.00 W spec platform spec envelope (not measured with this result) | NVIDIA Jetson Benchmarks (MLPerf v3.1 results table) 2026-10 |
| Intel Data Center GPU Flex 170 | 141 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Arc A-Series Graphics | 111 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Xeon Platinum 8380 CPU-only | 84.74 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| NVIDIA Jetson AGX Orin (MaxQ) | 74.71 FPS throughput_offline · b=unknown | MLPerf Retinanet INT8/FP16 (MLPerf closed) · TensorRT (MLPerf Inference, older round) · mid-size CNN | D | 22.27 W measured reported in result source — measured | NVIDIA Jetson Benchmarks (MLPerf v3.1 results table) 2026-10 |
| AMD Alveo V70 (Versal AI Core, XDNA AIE-ML) | 70.16 FPS E2E throughput, multi thread · b=unknown | tf_mlperf_resnet34_3.5 INT8 · Vitis AI 3.5 (VART) · mid-size CNN | D | 75.00 W spec reported in result source — spec | Vitis AI 3.5 Model Zoo performance table Older data (2023) |
| NVIDIA Jetson Orin NX 16GB | 66.50 FPS throughput_offline · b=unknown | MLPerf Retinanet INT8/FP16 (MLPerf closed) · TensorRT (MLPerf Inference, older round) · mid-size CNN | D | unknown power n/a no power published | NVIDIA Jetson Benchmarks (MLPerf v3.1 results table) 2026-10 |
| Intel Xeon Gold 6338N CPU-only | 60.95 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Xeon Platinum 8280 CPU-only | 58.17 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Arc B-Series Graphics | 58.10 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Core Ultra 9 288V | 52.88 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| NVIDIA Jetson Orin NX 16GB (MaxQ) | 47.59 FPS throughput_offline · b=unknown | MLPerf Retinanet INT8/FP16 (MLPerf closed) · TensorRT (MLPerf Inference, older round) · mid-size CNN | D | 15.57 W measured reported in result source — measured | NVIDIA Jetson Benchmarks (MLPerf v3.1 results table) 2026-10 |
| Intel Core Ultra 7 265H CPU-only | 47.07 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| AMD Versal AI Edge VEK280 (VE2802) | 40.67 FPS E2E throughput, multi thread · b=unknown | tf_mlperf_resnet34_3.5 INT8 · Vitis AI 3.5 (VART) · mid-size CNN | D | unknown power n/a no power published | Vitis AI 3.5 Model Zoo performance table Older data (2023) |
| AMD Versal AI Core VCK190 (VC1902) | 20.95 FPS E2E throughput, multi thread · b=unknown | tf_mlperf_resnet34_coco_1200_1200_433G INT8 · Vitis AI 3.0 (VART) · mid-size CNN | D | unknown power n/a no power published | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
| Intel Core Ultra 7 155H | 20.58 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Xeon Gold 5218T CPU-only | 17.60 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Core i7-12700H | 10.45 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Core i7-1355U CPU-only | 9.27 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Core i5-13600K CPU-only | 8.73 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Core i7-1185G7 CPU-only | 8.66 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| AMD Zynq UltraScale+ ZCU102 (ZU9EG) | 7.15 FPS E2E throughput, multi thread · b=unknown | tf_mlperf_resnet34_coco_1200_1200_433G INT8 · Vitis AI 3.0 (VART) · mid-size CNN | D | unknown power n/a no power published | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
| Intel Core i5-1335U | 5.65 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| AMD Kria KV260 Vision AI Starter Kit (K26 SOM) | 5.41 FPS E2E throughput, multi thread · b=unknown | tf_ssdresnet50v1_fpn_coco_640_640_178.4G INT8 · Vitis AI 3.0 (VART) · mid-size CNN | D | 7.50 W spec reported in result source — spec | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
| AMD Zynq UltraScale+ ZCU104 (ZU7EV) | 5.26 FPS E2E throughput, multi thread · b=unknown | tf_ssdresnet50v1_fpn_coco_640_640_178.4G INT8 · Vitis AI 3.0 (VART) · mid-size CNN | D | unknown power n/a no power published | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
| Intel Celeron 6305E CPU-only | 5.26 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Core i7-1185GRE CPU-only | 4.34 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Core i5-1235U CPU-only | 3.05 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Atom x7425E CPU-only | 2.52 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel N100 CPU-only | 1.97 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Atom X6425E CPU-only | 1.25 FPS throughput (OpenVINO benchmark_app) · b=unknown | ssd-resnet34-1200 INT8 · OpenVINO 2026.4.1 · mid-size CNN | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
medium (YOLO-m) · batch unknown (6 platforms)
✓ Like-for-like: model-size class medium (YOLO-m), batch unknown (size or batch not stated by source — unverified). Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| AMD Alveo V70 (Versal AI Core, XDNA AIE-ML) | 280 FPS E2E throughput, multi thread · b=unknown | pt_yolov6m_3.5 INT8 · Vitis AI 3.5 (VART) · medium (YOLO-m) | D | 75.00 W spec reported in result source — spec | Vitis AI 3.5 Model Zoo performance table Older data (2023) |
| AMD Versal AI Core VCK190 (VC1902) | 218 FPS E2E throughput, multi thread · b=unknown | pt_yolov6m_coco_640_640_82.4G INT8 · Vitis AI 3.0 (VART) · medium (YOLO-m) | D | unknown power n/a no power published | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
| AMD Versal AI Edge VEK280 (VE2802) | 49.61 FPS E2E throughput, multi thread · b=unknown | pt_yolov6m_3.5 INT8 · Vitis AI 3.5 (VART) · medium (YOLO-m) | D | unknown power n/a no power published | Vitis AI 3.5 Model Zoo performance table Older data (2023) |
| AMD Zynq UltraScale+ ZCU102 (ZU9EG) | 27.31 FPS E2E throughput, multi thread · b=unknown | pt_yolov6m_coco_640_640_82.4G INT8 · Vitis AI 3.0 (VART) · medium (YOLO-m) | D | unknown power n/a no power published | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
| AMD Zynq UltraScale+ ZCU104 (ZU7EV) | 24.53 FPS E2E throughput, multi thread · b=unknown | pt_yolov6m_coco_640_640_82.4G INT8 · Vitis AI 3.0 (VART) · medium (YOLO-m) | D | unknown power n/a no power published | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
| AMD Kria KV260 Vision AI Starter Kit (K26 SOM) | 20.12 FPS E2E throughput, multi thread · b=unknown | pt_yolov6m_coco_640_640_82.4G INT8 · Vitis AI 3.0 (VART) · medium (YOLO-m) | D | 7.50 W spec reported in result source — spec | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
mobile-class CNN · batch unknown (6 platforms)
✓ Like-for-like: model-size class mobile-class CNN, batch unknown (size or batch not stated by source — unverified). Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| AMD Alveo V70 (Versal AI Core, XDNA AIE-ML) | 6100 FPS E2E throughput, multi thread · b=unknown | tf_ssdmobilenetv1_3.5 INT8 · Vitis AI 3.5 (VART) · mobile-class CNN | D | 75.00 W spec reported in result source — spec | Vitis AI 3.5 Model Zoo performance table Older data (2023) |
| AMD Versal AI Edge VEK280 (VE2802) | 1933 FPS E2E throughput, multi thread · b=unknown | tf_ssdmobilenetv1_3.5 INT8 · Vitis AI 3.5 (VART) · mobile-class CNN | D | unknown power n/a no power published | Vitis AI 3.5 Model Zoo performance table Older data (2023) |
| AMD Versal AI Core VCK190 (VC1902) | 523 FPS E2E throughput, multi thread · b=unknown | tf_ssdmobilenetv1_coco_300_300_2.47G INT8 · Vitis AI 3.0 (VART) · mobile-class CNN | D | unknown power n/a no power published | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
| AMD Zynq UltraScale+ ZCU102 (ZU9EG) | 365 FPS E2E throughput, multi thread · b=unknown | tf_ssdmobilenetv1_coco_300_300_2.47G INT8 · Vitis AI 3.0 (VART) · mobile-class CNN | D | unknown power n/a no power published | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
| AMD Zynq UltraScale+ ZCU104 (ZU7EV) | 315 FPS E2E throughput, multi thread · b=unknown | tf_ssdmobilenetv1_coco_300_300_2.47G INT8 · Vitis AI 3.0 (VART) · mobile-class CNN | D | unknown power n/a no power published | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
| AMD Kria KV260 Vision AI Starter Kit (K26 SOM) | 174 FPS E2E throughput, multi thread · b=unknown | tf_ssdmobilenetv1_coco_300_300_2.47G INT8 · Vitis AI 3.0 (VART) · mobile-class CNN | D | 7.50 W spec reported in result source — spec | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
small (YOLO-s) · batch unknown (4 platforms)
✓ Like-for-like: model-size class small (YOLO-s), batch unknown (size or batch not stated by source — unverified). Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| AMD Versal AI Core VCK190 (VC1902) | 70.67 FPS E2E throughput, multi thread · b=unknown | pt_yolov5s6_coco_1280_1280_17G INT8 · Vitis AI 3.0 (VART) · small (YOLO-s) | D | unknown power n/a no power published | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
| AMD Zynq UltraScale+ ZCU102 (ZU9EG) | 26.09 FPS E2E throughput, multi thread · b=unknown | pt_yolov5s6_coco_1280_1280_17G INT8 · Vitis AI 3.0 (VART) · small (YOLO-s) | D | unknown power n/a no power published | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
| AMD Zynq UltraScale+ ZCU104 (ZU7EV) | 25.43 FPS E2E throughput, multi thread · b=unknown | pt_yolov5s6_coco_1280_1280_17G INT8 · Vitis AI 3.0 (VART) · small (YOLO-s) | D | unknown power n/a no power published | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
| AMD Kria KV260 Vision AI Starter Kit (K26 SOM) | 14.79 FPS E2E throughput, multi thread · b=unknown | pt_yolov5s6_coco_1280_1280_17G INT8 · Vitis AI 3.0 (VART) · small (YOLO-s) | D | 7.50 W spec reported in result source — spec | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
unknown · batch 1 (7 platforms)
✓ Like-for-like: model-size class unknown, batch 1 (size or batch not stated by source — unverified). Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Qualcomm Snapdragon X2 Elite (CRD) | 1502 FPS inference_time · b=1 | yolov8_det / YOLOv8-Detection w8a8 · Qualcomm AI Hub onnx (QAIRT 2.50.0.260828221209) · unknown | D | unknown power n/a no power published | Qualcomm AI Hub Models perf.yaml (BSD-3) 2026 (year only) |
| Qualcomm Dragonwing IQ-9075 EVK | 674 FPS inference_time · b=1 | yolov8_det / YOLOv8-Detection w8a8 · Qualcomm AI Hub tflite (QAIRT 2.50.0.260828221209) · unknown | D | unknown power n/a no power published | Qualcomm AI Hub Models perf.yaml (BSD-3) 2026 (year only) |
| Qualcomm Snapdragon X Elite (CRD) | 633 FPS inference_time · b=1 | yolov8_det / YOLOv8-Detection w8a8 · Qualcomm AI Hub onnx (QAIRT 2.50.0.260828221209) · unknown | D | unknown power n/a no power published | Qualcomm AI Hub Models perf.yaml (BSD-3) 2026 (year only) |
| Qualcomm Dragonwing RB3 Gen 2 (QCS6490) | 276 FPS inference_time · b=1 | yolov8_det / YOLOv8-Detection w8a8 · Qualcomm AI Hub tflite (QAIRT 2.50.0.260828221209) · unknown | D | unknown power n/a no power published | Qualcomm AI Hub Models perf.yaml (BSD-3) 2026 (year only) |
| AMD Ryzen AI processor (SKU not stated) | 144 FPS latency · b=1 | Yolo face v8n-v2 (AMD custom single-class YOLO) A8W8 (Quark) · ONNX Runtime + Vitis AI EP (Ryzen AI SW) · unknown | D | unknown power n/a no power published | AMD technical article: AI inference acceleration on Ryzen AI with Quark (Table 5) 2025 (year only) |
| TI AM68A (8 TOPS) | 83.75 FPS inference_time · b=1 | yolov7_tiny INT8 · TI Edge AI SDK / TIDL (edgeai-benchmark) · unknown | C | unknown power n/a no power published | TI edgeai-tensorlab tech report: speed/accuracy of object detection models (AM68A) undated |
| Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox) | 58.05 FPS inference_time · b=1 | 132_YOLOX INT8 (VNNX) · VectorBlox SDK (VNNX), no compression · unknown | D | unknown power n/a no power published | Microchip VectorBlox SDK tutorial metrics undated |
unknown · batch unknown (37 platforms)
✓ Like-for-like: model-size class unknown, batch unknown (size or batch not stated by source — unverified). Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Intel Xeon Platinum 6972P CPU-only | 5703 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n BF16 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Xeon Platinum 8580 CPU-only | 3545 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n BF16 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Xeon Platinum 8480+ CPU-only | 2433 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n BF16 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| AMD Alveo V70 (Versal AI Core, XDNA AIE-ML) | 2174 FPS E2E throughput, multi thread · b=unknown | pt_face-mask-detection_3.5 INT8 · Vitis AI 3.5 (VART) · unknown | D | 75.00 W spec reported in result source — spec | Vitis AI 3.5 Model Zoo performance table Older data (2023) |
| Intel Xeon Platinum 8380 CPU-only | 1714 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n INT8 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| AMD Versal AI Edge VEK280 (VE2802) | 1465 FPS E2E throughput, multi thread · b=unknown | tf_RefineDet-Medical_0.88_3.5 INT8 · Vitis AI 3.5 (VART) · unknown | D | unknown power n/a no power published | Vitis AI 3.5 Model Zoo performance table Older data (2023) |
| AMD Versal AI Core VCK190 (VC1902) | 1300 FPS E2E throughput, multi thread · b=unknown | tf_RefineDet-Medical_EDD_320_320_0.88_9.83G INT8 · Vitis AI 3.0 (VART) · unknown | D | unknown power n/a no power published | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
| Intel Xeon Gold 6338N CPU-only | 1233 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n INT8 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Arc B-Series Graphics | 1140 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n FP16 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Xeon Platinum 8280 CPU-only | 1028 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n INT8 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Data Center GPU Flex 170 | 813 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n INT8 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Arc A-Series Graphics | 595 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n INT8 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| AMD Zynq UltraScale+ ZCU102 (ZU9EG) | 539 FPS E2E throughput, multi thread · b=unknown | pt_yolox-nano_coco_416_416_1G INT8 · Vitis AI 3.0 (VART) · unknown | D | unknown power n/a no power published | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
| Intel Core Ultra 9 288V | 527 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n FP16 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| AMD Zynq UltraScale+ ZCU104 (ZU7EV) | 463 FPS E2E throughput, multi thread · b=unknown | pt_yolox-nano_coco_416_416_1G INT8 · Vitis AI 3.0 (VART) · unknown | D | unknown power n/a no power published | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
| Intel Xeon Gold 5218T CPU-only | 452 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n INT8 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Core Ultra 7 155H | 399 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n INT8 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| AMD Kria KV260 Vision AI Starter Kit (K26 SOM) | 276 FPS E2E throughput, multi thread · b=unknown | pt_yolox-nano_coco_416_416_1G INT8 · Vitis AI 3.0 (VART) · unknown | D | 7.50 W spec reported in result source — spec | Vitis AI 3.0 Model Zoo performance table Older data (2023) |
| Intel Core i5-13600K CPU-only | 263 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n INT8 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Core i7-12700H CPU-only | 262 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n INT8 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Core i7-1355U | 202 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n INT8 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Core i7-1185G7 CPU-only | 186 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n INT8 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Core Ultra 7 265H CPU-only | 164 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n FP16 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Dell PowerEdge XE7745 (8x NVIDIA L40S) | 154 FPS throughput_offline · b=unknown | MLPerf yolo-95 fp4 · TensorRT 10.14, CUDA 12.9 · unknown | A | unknown power n/a no power published | MLPerf Inference v6.0 (closed, edge) ID 6.0-0029 undated |
| HPE ProLiant Compute DL345 Gen12 (1x NVIDIA RTX PRO 4500 Blackwell Server Edition) | 146 FPS throughput_offline · b=unknown | MLPerf yolo-95 fp32 · PyTorch v2.13.0 · unknown | A | unknown power n/a no power published | MLPerf Inference v6.1 (closed, edge) ID HPE_PROLIANT_DL345_GEN12_RTX_PRO_4500_PCIE_32GBx1 undated |
| Intel Core i5-1335U | 131 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n INT8 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Celeron 6305E | 119 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n INT8 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Core i7-1185GRE | 117 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n INT8 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Dell PowerEdge XE7745 (16x NVIDIA L4-PCIe-24GB) | 102 FPS throughput_offline · b=unknown | MLPerf yolo-95 fp4 · CUDA 13.1 · unknown | A | unknown power n/a no power published | MLPerf Inference v6.0 (closed, edge) ID 6.0-0030 undated |
| Dell Pro Max with GB10 | 78.73 FPS throughput_offline · b=unknown | MLPerf yolo-95 fp4 · CUDA 13.0 · unknown | A | unknown power n/a no power published | MLPerf Inference v6.1 (closed, edge) ID Dell_Pro_Max_GB10x1 undated |
| Intel Core i5-1235U CPU-only | 77.79 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n INT8 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| HPE ProLiant Compute DL380 Gen12 (1x NVIDIA RTX PRO 4500 Blackwell Server Edition) | 72.19 FPS throughput_offline · b=unknown | MLPerf yolo-95 fp32 · PyTorch v2.13.0 · unknown | A | unknown power n/a no power published | MLPerf Inference v6.1 (closed, edge) ID HPE_PROLIANT_DL380_RTX_PRO_4500_PCIE_32GBx1_TRT undated |
| Intel Atom x7425E CPU-only | 67.82 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n INT8 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel N100 CPU-only | 61.02 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n INT8 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Intel Atom X6425E CPU-only | 36.26 FPS throughput (OpenVINO benchmark_app) · b=unknown | yolo_v8n INT8 · OpenVINO 2026.4.1 · unknown | D | unknown power n/a no power published | OpenVINO official performance benchmarks (graph-data-ov.json) undated |
| Lenovo IdeaPad Gaming 3 15ARH05 (1x NVIDIA GeForce GTX 1650 Ti) | 24.19 FPS throughput_offline · b=unknown | MLPerf yolo-95 fp32 · pytorch v2.5.0a0 · unknown | A | unknown power n/a no power published | MLPerf Inference v6.0 (closed, edge) ID 6.0-0034 undated |
| GATE Overflow system (13th Gen Intel Core i9-13900K, CPU only) CPU-only | 12.07 FPS throughput_offline · b=unknown | MLPerf yolo-95 fp32 · pytorch v2.3.1 · unknown | A | unknown power n/a no power published | MLPerf Inference v6.0 (closed, edge) ID 6.0-0036 undated |
How to read these numbers
Every number is labelled. Confidence: A MLPerf closed, audited · B documented third-party method · C community / review · D vendor-published, not independently verified · E estimate. Power basis: measured with the result · spec vendor spec/envelope · power n/a not published.
Machine-readable: /find.json (see llms.txt); full tables are in “Show data”. Confidence grades: A audited MLPerf closed · B documented third-party · C community · D vendor-published · E estimate. Unknown values are shown as unknown, never estimated. Generated 2026-10-16 from public sources.