Rockchip RK3588 (NPU, single core of 3) vs TI AM68A (8 TOPS)

Close-up of a Rockchip RK3588 system-on-chip package on a circuit board — Rockchip RK3588 SoC package. Photo: Popolon (Commons uploader; CC0, attribution not required), CC0, via Wikimedia Commons.

Texas Instrumentsedge SoCNo licensed photo yet

TI AM68A (8 TOPS) is faster in the only like-for-like comparison (largest gap: object detection, 1.14×).

	Rockchip RK3588 (NPU, single core of 3)	TI AM68A (8 TOPS)
Best object detection	109 FPS C 2026-10-13 (page last edited)	83.75 FPS C Older data (2024)
Power	n/a	n/a
Perf / W	n/a	n/a
Price	n/a	$174.197 list
Workloads with data	5 of 7	1 of 7

Best published object detection 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

✓ 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
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) Older data (2024)
Rockchip RK3588 (NPU, single core of 3)	73.60 FPS throughput · b=1	yolov7-tiny INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · unknown	C	unknown power n/a no power published	Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited)

instance segmentation

Only Rockchip RK3588 (NPU, single core of 3) has published instance segmentation results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Rockchip RK3588 (NPU, single core of 3)	71.50 FPS throughput · b=1	yolov5n-seg INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · nano (YOLO-n)	C	unknown power n/a no power published	Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited)

TI AM68A (8 TOPS):

◌

No published instance segmentation results for TI AM68A (8 TOPS) or Rockchip RK3588 (NPU, single core of 3) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

pose estimation

Only Rockchip RK3588 (NPU, single core of 3) has published pose estimation results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Rockchip RK3588 (NPU, single core of 3)	58.30 FPS throughput · b=1	yolov8n-pose INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · nano (YOLO-n)	C	unknown power n/a no power published	Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited)

TI AM68A (8 TOPS):

◌

No published pose estimation results for TI AM68A (8 TOPS) or Rockchip RK3588 (NPU, single core of 3) 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 Rockchip RK3588 (NPU, single core of 3) has published image classification results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Rockchip RK3588 (NPU, single core of 3)	459 FPS throughput · b=1	mobilenetv2-12 INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · mobile-class CNN	C	unknown power n/a no power published	Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited)

TI AM68A (8 TOPS):

◌

No published image classification results for TI AM68A (8 TOPS) or Rockchip RK3588 (NPU, single core of 3) 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 Rockchip RK3588 (NPU, single core of 3) has published semantic segmentation results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Rockchip RK3588 (NPU, single core of 3)	34.70 FPS throughput · b=1	deeplab-v3-plus-mobilenet-v2 INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · mobile-class CNN	C	unknown power n/a no power published	Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited)

TI AM68A (8 TOPS):

◌

No published semantic segmentation results for TI AM68A (8 TOPS) or Rockchip RK3588 (NPU, single core of 3) 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 Rockchip RK3588 (NPU, single core of 3) or TI AM68A (8 TOPS) 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 Rockchip RK3588 (NPU, single core of 3) or TI AM68A (8 TOPS) 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.