HWBench

Apple Mac mini M4 Pro 64GB vs Rockchip RK3588 (NPU, single core of 3)

Apple Mac mini (M4, 2024), small silver aluminium desktop, front view
Apple Mac mini (M4, 2024) — the M4 Pro model shares this enclosure. Photo: Seasider53, CC BY 4.0, via Wikimedia Commons.
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.

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

Apple Mac mini M4 Pro 64GBRockchip RK3588 (NPU, single core of 3)
Best LLM generation5.48 tok/s C
2026-03-20 (page last edited)
n/a
Power80.00 W measuredn/a
Perf / W0.0685 tok/s/W measuredn/a
Pricen/an/a
Workloads with data1 of 75 of 7

Best published LLM generation result per platform. n/a = not published; never estimated.

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

object detection

Only Rockchip RK3588 (NPU, single core of 3) has published object detection results.

PlatformResultModel · precision · stackGradePowerSource
Rockchip RK3588 (NPU, single core of 3)66.50 FPS
throughput · b=1
yolov5s_relu
INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · small (YOLO-s)
Cunknown power n/a
no power published
Rockchip rknn_model_zoo README benchmark table
2026-10-13 (page last edited)

Apple Mac mini M4 Pro 64GB:

◌

No published object detection results for Apple Mac mini M4 Pro 64GB 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.

instance segmentation

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

PlatformResultModel · precision · stackGradePowerSource
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)
Cunknown power n/a
no power published
Rockchip rknn_model_zoo README benchmark table
2026-10-13 (page last edited)

Apple Mac mini M4 Pro 64GB:

◌

No published instance segmentation results for Apple Mac mini M4 Pro 64GB 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.

PlatformResultModel · precision · stackGradePowerSource
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)
Cunknown power n/a
no power published
Rockchip rknn_model_zoo README benchmark table
2026-10-13 (page last edited)

Apple Mac mini M4 Pro 64GB:

◌

No published pose estimation results for Apple Mac mini M4 Pro 64GB 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.

PlatformResultModel · precision · stackGradePowerSource
Rockchip RK3588 (NPU, single core of 3)459 FPS
throughput · b=1
mobilenetv2-12
INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · mobile-class CNN
Cunknown power n/a
no power published
Rockchip rknn_model_zoo README benchmark table
2026-10-13 (page last edited)

Apple Mac mini M4 Pro 64GB:

◌

No published image classification results for Apple Mac mini M4 Pro 64GB 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.

PlatformResultModel · precision · stackGradePowerSource
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
Cunknown power n/a
no power published
Rockchip rknn_model_zoo README benchmark table
2026-10-13 (page last edited)

Apple Mac mini M4 Pro 64GB:

◌

No published semantic segmentation results for Apple Mac mini M4 Pro 64GB 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 Apple Mac mini M4 Pro 64GB 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.

LLM generation

Only Apple Mac mini M4 Pro 64GB has published LLM generation results.

PlatformResultModel · precision · stackGradePowerSource
Apple Mac mini M4 Pro 64GB5.48 tok/s
tg · b=unknown
70B-class LLM (Q4)
~Q4 · as reviewed (Ollama/llama.cpp class) · LLM >40B
C80.00 W measured
reported in result source — measured
vminstall.com review
2026-03-20 (page last edited)

Rockchip RK3588 (NPU, single core of 3):

◌

No published LLM generation results for Rockchip RK3588 (NPU, single core of 3) or Apple Mac mini M4 Pro 64GB 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.