Axelera Metis Embedded 113m M.2 card vs Minisforum MS-R1 (as tested by Jeff Geerling)
No like-for-like comparison yet: both have published results, but model size or batch differ. Treat the numbers below as indicative only.
| Axelera Metis Embedded 113m M.2 card | Minisforum MS-R1 (as tested by Jeff Geerling) | |
|---|---|---|
| Best object detection | 3004 FPS C 2026-10-15 (page last edited) | n/a |
| Power | 9.00 W Module TDP, Module, max of range 3.5-9 W | n/a |
| Perf / W | 334 FPS/W Module TDP, Module, max of range 3.5-9 W | n/a |
| Price | n/a | n/a |
| Workloads with data | 5 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 Axelera Metis Embedded 113m M.2 card has published object detection results.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Axelera Metis Embedded 113m M.2 card | 91.00 FPS throughput · b=1 | RetinaFace - Resnet50 INT8 · Voyager SDK (GStreamer pipeline) · mid-size CNN | C | 9.00 W Module TDP, Module, max of range 3.5-9 W reported in result source — Module TDP, Module, max of range 3.5-9 W | Axelera Voyager SDK model zoo (docs/reference/models/model-zoo.md) 2026-10-15 (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 Axelera Metis Embedded 113m M.2 card 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 Axelera Metis Embedded 113m M.2 card has published instance segmentation results.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Axelera Metis Embedded 113m M.2 card | 186 FPS throughput · b=1 | YOLACT-ResNet50 INT8 · Voyager SDK (GStreamer pipeline) · mid-size CNN | C | 9.00 W Module TDP, Module, max of range 3.5-9 W reported in result source — Module TDP, Module, max of range 3.5-9 W | Axelera Voyager SDK model zoo (docs/reference/models/model-zoo.md) 2026-10-15 (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 Axelera Metis Embedded 113m M.2 card 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 Axelera Metis Embedded 113m M.2 card has published pose estimation results.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Axelera Metis Embedded 113m M.2 card | 746 FPS throughput · b=1 | YOLOv8n-pose INT8 · Voyager SDK (GStreamer pipeline) · nano (YOLO-n) | C | 9.00 W Module TDP, Module, max of range 3.5-9 W reported in result source — Module TDP, Module, max of range 3.5-9 W | Axelera Voyager SDK model zoo (docs/reference/models/model-zoo.md) 2026-10-15 (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 Axelera Metis Embedded 113m M.2 card 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 Axelera Metis Embedded 113m M.2 card has published image classification results.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Axelera Metis Embedded 113m M.2 card | 4257 FPS throughput · b=1 | MobileNetV4-small INT8 · Voyager SDK (GStreamer pipeline) · mobile-class CNN | C | 9.00 W Module TDP, Module, max of range 3.5-9 W reported in result source — Module TDP, Module, max of range 3.5-9 W | Axelera Voyager SDK model zoo (docs/reference/models/model-zoo.md) 2026-10-15 (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 Axelera Metis Embedded 113m M.2 card 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 Axelera Metis Embedded 113m M.2 card has published semantic segmentation results.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Axelera Metis Embedded 113m M.2 card | 294 FPS throughput · b=1 | YOLO26n-sem INT8 · Voyager SDK (GStreamer pipeline) · nano (YOLO-n) | C | 9.00 W Module TDP, Module, max of range 3.5-9 W reported in result source — Module TDP, Module, max of range 3.5-9 W | Axelera Voyager SDK model zoo (docs/reference/models/model-zoo.md) 2026-10-15 (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 Axelera Metis Embedded 113m M.2 card 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 Axelera Metis Embedded 113m M.2 card 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.
LLM generation
Only Minisforum MS-R1 (as tested by Jeff Geerling) has published LLM generation results.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| 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 | C | unknown power not published not published | Jeff Geerling ai-benchmarks issue results (comments) 2025-11-10 (page last edited) |
Axelera Metis Embedded 113m M.2 card:
No published LLM generation results for Axelera Metis Embedded 113m M.2 card 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