AMD Versal AI Edge Series Gen 2 VEK385 vs Google Coral Dev Board (Edge TPU)

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.

AMDeval kit (adaptive SoC)No licensed photo yet

Googleedge SBCNo licensed photo yet

Showing the newest results per platform and source. 18 superseded older results are hidden.Showing all results, including 18 superseded by newer results from the same source.

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

	AMD Versal AI Edge Series Gen 2 VEK385	Google Coral Dev Board (Edge TPU)
Best object detection	93.50 FPS D 2026-09-24 (published)	n/a
Power	n/a	n/a
Perf / W	n/a	n/a
Price	$15995 list	n/a
Workloads with data	2 of 7	1 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

Only AMD Versal AI Edge Series Gen 2 VEK385 has published object detection results.

Platform	Result	Model · precision · stack	Grade	Power	Source
AMD Versal AI Edge Series Gen 2 VEK385	93.50 FPS throughput · b=1	yolov8m VINT8 with BF16 tail (Quark) · Vitis AI 6.3 VART ml_vart --benchmark --runs 100 · medium (YOLO-m)	D	unknown power n/a no power published	AMD Vitis AI 6.3 VEK385 YOLOv8m tutorial 2026-09-24 (published)

Google Coral Dev Board (Edge TPU):

◌

No published object detection results for Google Coral Dev Board (Edge TPU) or AMD Versal AI Edge Series Gen 2 VEK385 yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

instance segmentation

◌

No published instance segmentation results for AMD Versal AI Edge Series Gen 2 VEK385 or Google Coral Dev Board (Edge TPU) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

pose estimation

◌

No published pose estimation results for AMD Versal AI Edge Series Gen 2 VEK385 or Google Coral Dev Board (Edge TPU) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

image classification

Only AMD Versal AI Edge Series Gen 2 VEK385 has published image classification results.

Platform	Result	Model · precision · stack	Grade	Power	Source
AMD Versal AI Edge Series Gen 2 VEK385	265 FPS throughput · b=1	resnet50-v1-12 (ONNX) INT8 (Quark) · Vitis AI 6.3 ONNX Runtime Vitis AI EP (evaluate.py, Python loop) · mid-size CNN	D	unknown power n/a no power published	AMD Vitis AI 6.3 VEK385 ResNet50 Quark tutorial 2026-09-23 (page last edited)

Google Coral Dev Board (Edge TPU):

◌

No published image classification results for Google Coral Dev Board (Edge TPU) or AMD Versal AI Edge Series Gen 2 VEK385 yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

semantic segmentation

Only Google Coral Dev Board (Edge TPU) has published semantic segmentation results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Google Coral Dev Board (Edge TPU)	175 FPS inference_time · b=1	Unet Mv2 (128x128) INT8 · TensorFlow Lite C++ benchmark (Edge TPU runtime) · mid-size CNN	D	2.00 W spec platform spec envelope (not measured with this result)	Google Coral Edge TPU benchmarks page (Table 1) Older data (2020)

AMD Versal AI Edge Series Gen 2 VEK385:

◌

No published semantic segmentation results for AMD Versal AI Edge Series Gen 2 VEK385 or Google Coral Dev Board (Edge TPU) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

speech-to-text

◌

No published speech-to-text results for AMD Versal AI Edge Series Gen 2 VEK385 or Google Coral Dev Board (Edge TPU) 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 Series Gen 2 VEK385 or Google Coral Dev Board (Edge TPU) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

AMD Versal AI Edge Series Gen 2 VEK385 is faster in the only like-for-like comparison (largest gap: image classification, 14.87×).

	AMD Versal AI Edge Series Gen 2 VEK385	Google Coral Dev Board (Edge TPU)
Best image classification	265 FPS D 2026-09-23 (page last edited)	500 FPS D Older data (2019)
Power	n/a	2.00 W spec
Perf / W	n/a	250 FPS/W spec
Price	$15995 list	n/a
Workloads with data	2 of 7	3 of 7

Best published image classification result per platform (may be from different like-for-like groups — see data). 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 mobile-class CNN at batch 1. Differs: model-size class medium (YOLO-m) vs mobile-class CNN.

Platform	Result	Model · precision · stack	Grade	Power	Source
Google Coral Dev Board (Edge TPU)	90.91 FPS inference_time · b=1	MobileNet v1 SSD (224x224) INT8 · TensorFlow Lite C++ benchmark (Edge TPU runtime) · mobile-class CNN	D	2.00 W spec platform spec envelope (not measured with this result)	Google Coral Edge TPU benchmarks page (Table 1) Older data (2019)
AMD Versal AI Edge Series Gen 2 VEK385 MIXED: model-size class medium (YOLO-m) vs mobile-class CNN	93.50 FPS throughput · b=1	yolov8m VINT8 with BF16 tail (Quark) · Vitis AI 6.3 VART ml_vart --benchmark --runs 100 · medium (YOLO-m)	D	unknown power n/a no power published	AMD Vitis AI 6.3 VEK385 YOLOv8m tutorial 2026-09-24 (published)

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

instance segmentation

◌

pose estimation

◌

image classification

✓ Like-for-like: model-size class mid-size CNN, batch 1. Model, precision and stack may still differ.

Platform	Result	Model · precision · stack	Grade	Power	Source
AMD Versal AI Edge Series Gen 2 VEK385	265 FPS throughput · b=1	resnet50-v1-12 (ONNX) INT8 (Quark) · Vitis AI 6.3 ONNX Runtime Vitis AI EP (evaluate.py, Python loop) · mid-size CNN	D	unknown power n/a no power published	AMD Vitis AI 6.3 VEK385 ResNet50 Quark tutorial 2026-09-23 (page last edited)
Google Coral Dev Board (Edge TPU)	17.86 FPS inference_time · b=1	ResNet-50 V1 (299x299) INT8 · TensorFlow Lite C++ benchmark (Edge TPU runtime) · mid-size CNN	D	2.00 W spec platform spec envelope (not measured with this result)	Google Coral Edge TPU benchmarks page (Table 1) Older data (2019)

semantic segmentation

Only Google Coral Dev Board (Edge TPU) has published semantic segmentation results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Google Coral Dev Board (Edge TPU)	175 FPS inference_time · b=1	Unet Mv2 (128x128) INT8 · TensorFlow Lite C++ benchmark (Edge TPU runtime) · mid-size CNN	D	2.00 W spec platform spec envelope (not measured with this result)	Google Coral Edge TPU benchmarks page (Table 1) Older data (2020)

AMD Versal AI Edge Series Gen 2 VEK385:

◌

speech-to-text

◌

LLM generation

◌

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.