AMD Versal AI Edge VEK280 (VE2802): edge AI benchmarks

Name: AMD Versal AI Edge VEK280 (VE2802)
Brand: AMD

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 licensed photo available — placeholder drawing.

Vendor AMDForm factor eval kit (adaptive SoC)Compute DPU (AIE-ML)Indicative price unknownPower envelope unknownPublished rows 182

object detection1933 FPSD perf/W n/aOlder data (2023)

pose estimation428 FPSD perf/W n/aOlder data (2023)

image classification8598 FPSD perf/W n/aOlder data (2023)

semantic segmentation1564 FPSD perf/W n/aOlder data (2023)

Best published result per workload, across model sizes — open “Show data” for like-for-like groups.

Show data — per-workload tables

object detection

Like-for-like group	Best result	Model · precision · stack	Grade	Power	Source · date	Rank in group
medium (YOLO-m) · b=unknown	49.61 FPS	pt_yolov6m_3.5 INT8 · Vitis AI 3.5 (VART)	D	unknown power n/a	Vitis AI 3.5 Model Zoo performance table Older data (2023)	3 of 6
mid-size CNN · b=unknown	40.67 FPS	tf_mlperf_resnet34_3.5 INT8 · Vitis AI 3.5 (VART)	D	unknown power n/a	Vitis AI 3.5 Model Zoo performance table Older data (2023)	17 of 34
mobile-class CNN · b=unknown	1933 FPS	tf_ssdmobilenetv1_3.5 INT8 · Vitis AI 3.5 (VART)	D	unknown power n/a	Vitis AI 3.5 Model Zoo performance table Older data (2023)	2 of 6
unknown · b=unknown	1465 FPS	tf_RefineDet-Medical_0.88_3.5 INT8 · Vitis AI 3.5 (VART)	D	unknown power n/a	Vitis AI 3.5 Model Zoo performance table Older data (2023)	6 of 37

instance segmentation

◌

No published instance segmentation results for AMD Versal AI Edge VEK280 (VE2802) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

pose estimation

Like-for-like group	Best result	Model · precision · stack	Grade	Power	Source · date	Rank in group
unknown · b=unknown	428 FPS	pt_movenet_3.5 INT8 · Vitis AI 3.5 (VART)	D	unknown power n/a	Vitis AI 3.5 Model Zoo performance table Older data (2023)	3 of 6

image classification

Like-for-like group	Best result	Model · precision · stack	Grade	Power	Source · date	Rank in group
mid-size CNN · b=unknown	6595 FPS	pt_OFA-resnet50_0.88_3.5 INT8 · Vitis AI 3.5 (VART)	D	unknown power n/a	Vitis AI 3.5 Model Zoo performance table Older data (2023)	9 of 41
mobile-class CNN · b=unknown	8381 FPS	tf_mobilenetv1-0.25_3.5 INT8 · Vitis AI 3.5 (VART)	D	unknown power n/a	Vitis AI 3.5 Model Zoo performance table Older data (2023)	9 of 31
unknown · b=unknown	8598 FPS	pt_squeezenet_3.5 INT8 · Vitis AI 3.5 (VART)	D	unknown power n/a	Vitis AI 3.5 Model Zoo performance table Older data (2023)	2 of 6

semantic segmentation

Like-for-like group	Best result	Model · precision · stack	Grade	Power	Source · date	Rank in group
mid-size CNN · b=unknown	1564 FPS	tf2_2D-UNET_3.5 INT8 · Vitis AI 3.5 (VART)	D	unknown power n/a	Vitis AI 3.5 Model Zoo performance table Older data (2023)	2 of 6
unknown · b=unknown	70.06 FPS	pt_pointpillars_3.5 INT8 · Vitis AI 3.5 (VART)	D	unknown power n/a	Vitis AI 3.5 Model Zoo performance table Older data (2023)	6 of 6

speech-to-text

◌

No published speech-to-text results for AMD Versal AI Edge VEK280 (VE2802) 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 Versal AI Edge VEK280 (VE2802) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

Compare with another platform (99)

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.