AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S) vs Rockchip RK3576 (NPU, single core of 2)

AMDAI mini-PCNo licensed photo yet

Rockchipedge SoCNo licensed photo yet

AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S) is faster in all 3 like-for-like comparisons (largest gap: object detection, 3.87×).

	AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S)	Rockchip RK3576 (NPU, single core of 2)
Best object detection	476 FPS B 2026-10-04 (page last edited)	123 FPS C 2026-10-13 (page last edited)
Power	120 W spec	n/a
Perf / W	3.97 FPS/W spec	n/a
Price	n/a	n/a
Workloads with data	2 of 7	5 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 nano (YOLO-n), batch 1. Model, precision and stack may still differ.

Platform	Result	Model · precision · stack	Grade	Power	Source
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 documentation: AMD ROCm/MIGraphX integration benchmark 2026-10-04 (page last edited)
Rockchip RK3576 (NPU, single core of 2)	123 FPS throughput · b=1	yolov5n 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)

✓ 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
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 documentation: AMD ROCm/MIGraphX integration benchmark 2026-10-04 (page last edited)
Rockchip RK3576 (NPU, single core of 2)	65.10 FPS throughput · b=1	yolov5s_relu INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · small (YOLO-s)	C	unknown power n/a no power published	Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited)

✓ 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
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 documentation: AMD ROCm/MIGraphX integration benchmark 2026-10-04 (page last edited)
Rockchip RK3576 (NPU, single core of 2)	24.10 FPS throughput · b=1	yolov5m INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · medium (YOLO-m)	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 RK3576 (NPU, single core of 2) has published instance segmentation results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Rockchip RK3576 (NPU, single core of 2)	96.40 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)

AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S):

◌

No published instance segmentation results for AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S) or Rockchip RK3576 (NPU, single core of 2) 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 RK3576 (NPU, single core of 2) has published pose estimation results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Rockchip RK3576 (NPU, single core of 2)	75.00 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)

AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S):

◌

No published pose estimation results for AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S) or Rockchip RK3576 (NPU, single core of 2) 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 RK3576 (NPU, single core of 2) has published image classification results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Rockchip RK3576 (NPU, single core of 2)	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)

AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S):

◌

No published image classification results for AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S) or Rockchip RK3576 (NPU, single core of 2) 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 RK3576 (NPU, single core of 2) has published semantic segmentation results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Rockchip RK3576 (NPU, single core of 2)	37.80 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)

AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S):

◌

No published semantic segmentation results for AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S) or Rockchip RK3576 (NPU, single core of 2) 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 Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S) or Rockchip RK3576 (NPU, single core of 2) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

LLM generation

Only AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S) has published LLM generation results.

Platform	Result	Model · precision · stack	Grade	Power	Source
AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S) CPU-only	11.37 tok/s generation_throughput · b=1	DeepSeek R1 14b as in linked issue (Ollama default tags are 4-bit) · Ollama / llama.cpp (see linked issue) · LLM 5–14B	C	140 W measured reported in result source — measured	Jeff Geerling ai-benchmarks README (Findings tables) 2026-09-22 (page last edited)

Rockchip RK3576 (NPU, single core of 2):

◌

No published LLM generation results for Rockchip RK3576 (NPU, single core of 2) or AMD Ryzen AI Max+ 395 / PRO 395 (Strix Halo, Radeon 8060S) 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.