HWBench

AMD Zynq UltraScale+ ZCU102 (ZU9EG) vs Axelera Metis Edge 130p PCIe card

FPGA / Versal coverage note: 1,243 rows come from the AMD Vitis AI 3.0/3.5 Model Zoo tables; 733 (59%) are image classification. Detection, segmentation and other workloads are thinner, and there is no LLM or speech data for these boards. All are vendor-published (grade D). FPGA / Versal overview.

No like-for-like comparison yet: both have published results, but model size or batch differ. Treat the numbers below as indicative only.

AMD Zynq UltraScale+ ZCU102 (ZU9EG)Axelera Metis Edge 130p PCIe card
Best object detection539 FPS D
Older data (2023)
2894 FPS C
2026-10-15 (page last edited)
Powern/an/a
Perf / Wn/an/a
Pricen/an/a
Workloads with data4 of 75 of 7

Best published object detection result per platform. n/a = not published; never estimated.

Show data — all workloads, sources and like-for-like groups

object detection

⚠ MIXED COMPARISON — not like-for-like. Baseline mid-size CNN at batch 1. Differs: model-size class unknown vs mid-size CNN; batch unknown vs 1.
PlatformResultModel · precision · stackGradePowerSource
Axelera Metis Edge 130p PCIe card89.00 FPS
throughput · b=1
RetinaFace - Resnet50
INT8 · Voyager SDK (GStreamer pipeline) · mid-size CNN
Cunknown power n/a
no power published
Axelera Voyager SDK model zoo (docs/reference/models/model-zoo.md)
2026-10-15 (page last edited)
AMD Zynq UltraScale+ ZCU102 (ZU9EG)
MIXED: model-size class unknown vs mid-size CNN; batch unknown vs 1
539 FPS
E2E throughput, multi thread · b=unknown
pt_yolox-nano_coco_416_416_1G
INT8 · Vitis AI 3.0 (VART) · unknown
Dunknown power n/a
no power published
Vitis AI 3.0 Model Zoo performance table
Older data (2023)

No shared like-for-like group exists for this pair.

instance segmentation

Only Axelera Metis Edge 130p PCIe card has published instance segmentation results.

PlatformResultModel · precision · stackGradePowerSource
Axelera Metis Edge 130p PCIe card287 FPS
throughput · b=1
YOLACT-ResNet50
INT8 · Voyager SDK (GStreamer pipeline) · mid-size CNN
Cunknown power n/a
no power published
Axelera Voyager SDK model zoo (docs/reference/models/model-zoo.md)
2026-10-15 (page last edited)

AMD Zynq UltraScale+ ZCU102 (ZU9EG):

◌

No published instance segmentation results for AMD Zynq UltraScale+ ZCU102 (ZU9EG) or Axelera Metis Edge 130p PCIe card yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

pose estimation

⚠ MIXED COMPARISON — not like-for-like. Baseline nano (YOLO-n) at batch 1. Differs: model-size class mobile-class CNN vs nano (YOLO-n); batch unknown vs 1.
PlatformResultModel · precision · stackGradePowerSource
Axelera Metis Edge 130p PCIe card762 FPS
throughput · b=1
YOLOv8n-pose
INT8 · Voyager SDK (GStreamer pipeline) · nano (YOLO-n)
Cunknown power n/a
no power published
Axelera Voyager SDK model zoo (docs/reference/models/model-zoo.md)
2026-10-15 (page last edited)
AMD Zynq UltraScale+ ZCU102 (ZU9EG)
MIXED: model-size class mobile-class CNN vs nano (YOLO-n); batch unknown vs 1
391 FPS
E2E throughput, multi thread · b=unknown
pt_movenet_coco_192_192_0.5G
INT8 · Vitis AI 3.0 (VART) · mobile-class CNN
Dunknown power n/a
no power published
Vitis AI 3.0 Model Zoo performance table
Older data (2023)

No shared like-for-like group exists for this pair.

image classification

⚠ MIXED COMPARISON — not like-for-like. Baseline mobile-class CNN at batch 1. Differs: batch unknown vs 1.
PlatformResultModel · precision · stackGradePowerSource
Axelera Metis Edge 130p PCIe card4591 FPS
throughput · b=1
MobileNetV4-small
INT8 · Voyager SDK (GStreamer pipeline) · mobile-class CNN
Cunknown power n/a
no power published
Axelera Voyager SDK model zoo (docs/reference/models/model-zoo.md)
2026-10-15 (page last edited)
AMD Zynq UltraScale+ ZCU102 (ZU9EG)
MIXED: batch unknown vs 1
4832 FPS
E2E throughput, multi thread · b=unknown
tf_mobilenetv1_0.25_imagenet_128_128_27M
INT8 · Vitis AI 3.0 (VART) · mobile-class CNN
Dunknown power n/a
no power published
Vitis AI 3.0 Model Zoo performance table
Older data (2023)

No shared like-for-like group exists for this pair.

semantic segmentation

⚠ MIXED COMPARISON — not like-for-like. Baseline nano (YOLO-n) at batch 1. Differs: model-size class mid-size CNN vs nano (YOLO-n); batch unknown vs 1.
PlatformResultModel · precision · stackGradePowerSource
Axelera Metis Edge 130p PCIe card280 FPS
throughput · b=1
YOLO26n-sem
INT8 · Voyager SDK (GStreamer pipeline) · nano (YOLO-n)
Cunknown power n/a
no power published
Axelera Voyager SDK model zoo (docs/reference/models/model-zoo.md)
2026-10-15 (page last edited)
AMD Zynq UltraScale+ ZCU102 (ZU9EG)
MIXED: model-size class mid-size CNN vs nano (YOLO-n); batch unknown vs 1
437 FPS
E2E throughput, multi thread · b=unknown
tf2_2d-unet_nuclei_128_128_5.31G
INT8 · Vitis AI 3.0 (VART) · mid-size CNN
Dunknown power n/a
no power published
Vitis AI 3.0 Model Zoo performance table
Older data (2023)

No shared like-for-like group exists for this pair.

speech-to-text

◌

No published speech-to-text results for AMD Zynq UltraScale+ ZCU102 (ZU9EG) or Axelera Metis Edge 130p PCIe card yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

LLM generation

◌

No published LLM generation results for AMD Zynq UltraScale+ ZCU102 (ZU9EG) or Axelera Metis Edge 130p PCIe card yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

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.