HWBench

Minisforum MS-R1 (as tested by Jeff Geerling) vs Rockchip RK3576 (NPU, single core of 2)

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

Minisforum MS-R1 (as tested by Jeff Geerling)Rockchip RK3576 (NPU, single core of 2)
Best LLM generation71.36 tok/s C
2025-11-10 (page last edited)
n/a
Powern/an/a
Perf / Wn/an/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 RK3576 (NPU, single core of 2) has published object detection results.

PlatformResultModel · precision · stackGradePowerSource
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)
Cunknown power not published
not published
Rockchip rknn_model_zoo README benchmark table
2026-10-13 (page last edited)

Minisforum MS-R1 (as tested by Jeff Geerling):

◌

No published object detection results for Minisforum MS-R1 (as tested by Jeff Geerling) 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.

instance segmentation

Only Rockchip RK3576 (NPU, single core of 2) has published instance segmentation results.

PlatformResultModel · precision · stackGradePowerSource
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)
Cunknown power not published
not published
Rockchip rknn_model_zoo README benchmark table
2026-10-13 (page last edited)

Minisforum MS-R1 (as tested by Jeff Geerling):

◌

No published instance segmentation results for Minisforum MS-R1 (as tested by Jeff Geerling) 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.

PlatformResultModel · precision · stackGradePowerSource
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)
Cunknown power not published
not published
Rockchip rknn_model_zoo README benchmark table
2026-10-13 (page last edited)

Minisforum MS-R1 (as tested by Jeff Geerling):

◌

No published pose estimation results for Minisforum MS-R1 (as tested by Jeff Geerling) 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.

PlatformResultModel · precision · stackGradePowerSource
Rockchip RK3576 (NPU, single core of 2)459 FPS
throughput · b=1
mobilenetv2-12
INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · mobile-class CNN
Cunknown power not published
not published
Rockchip rknn_model_zoo README benchmark table
2026-10-13 (page last edited)

Minisforum MS-R1 (as tested by Jeff Geerling):

◌

No published image classification results for Minisforum MS-R1 (as tested by Jeff Geerling) 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.

PlatformResultModel · precision · stackGradePowerSource
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
Cunknown power not published
not published
Rockchip rknn_model_zoo README benchmark table
2026-10-13 (page last edited)

Minisforum MS-R1 (as tested by Jeff Geerling):

◌

No published semantic segmentation results for Minisforum MS-R1 (as tested by Jeff Geerling) 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 Minisforum MS-R1 (as tested by Jeff Geerling) 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 Minisforum MS-R1 (as tested by Jeff Geerling) has published LLM generation results.

PlatformResultModel · precision · stackGradePowerSource
Minisforum MS-R1 (as tested by Jeff Geerling)34.52 tok/s
generation_throughput · b=1
llama3.1:8b
Ollama default tag (4-bit unless tag says otherwise) · Ollama (geerlingguy/ollama-benchmark) · LLM 5–14B
Cunknown power not published
not published
Jeff Geerling ai-benchmarks issue results (comments)
2025-11-10 (page last edited)

Rockchip RK3576 (NPU, single core of 2):

◌

No published LLM generation results for Rockchip RK3576 (NPU, single core of 2) or Minisforum MS-R1 (as tested by Jeff Geerling) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

Grades: A audited MLPerf · B third-party · C community · D vendor. How we rank · JSON