HWBench

Axelera Metis Edge 130p PCIe card (16GB) vs Minisforum MS-R1 (as tested by Jeff Geerling)

Minisforum MS-R1 (as tested by Jeff Geerling) is faster in all 2 like-for-like comparisons (largest gap: LLM generation, 12.79×).

Axelera Metis Edge 130p PCIe card (16GB)Minisforum MS-R1 (as tested by Jeff Geerling)
Best LLM generation33.80 tok/s C
2026-10-15 (page last edited)
71.36 tok/s C
2025-11-10 (page last edited)
Powern/an/a
Perf / Wn/an/a
Pricen/an/a
Workloads with data1 of 71 of 7

Best published LLM generation 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

◌

No published object detection results for Axelera Metis Edge 130p PCIe card (16GB) 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.

instance segmentation

◌

No published instance segmentation results for Axelera Metis Edge 130p PCIe card (16GB) 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.

pose estimation

◌

No published pose estimation results for Axelera Metis Edge 130p PCIe card (16GB) 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.

image classification

◌

No published image classification results for Axelera Metis Edge 130p PCIe card (16GB) 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.

semantic segmentation

◌

No published semantic segmentation results for Axelera Metis Edge 130p PCIe card (16GB) 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.

speech-to-text

◌

No published speech-to-text results for Axelera Metis Edge 130p PCIe card (16GB) 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

✓ Like-for-like: model-size class LLM 5–14B, batch 1. Model, precision and stack may still differ.
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)
Axelera Metis Edge 130p PCIe card (16GB)2.70 tok/s
generation_throughput · b=1
qwen3-8b
not stated · Voyager SDK model_axscript.llm · LLM 5–14B
Cunknown power not published
not published
Axelera Voyager SDK model zoo (docs/reference/models/model-zoo.md)
2026-10-15 (page last edited)
✓ Like-for-like: model-size class LLM ≤4B, batch 1. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
Minisforum MS-R1 (as tested by Jeff Geerling)71.36 tok/s
generation_throughput · b=1
llama3.2:3b
Ollama default tag (4-bit unless tag says otherwise) · Ollama (geerlingguy/ollama-benchmark) · LLM ≤4B
Cunknown power not published
not published
Jeff Geerling ai-benchmarks issue results (comments)
2025-11-10 (page last edited)
Axelera Metis Edge 130p PCIe card (16GB)19.40 tok/s
generation_throughput · b=1
qwen3-0.6b
not stated · Voyager SDK model_axscript.llm · LLM ≤4B
Cunknown power not published
not published
Axelera Voyager SDK model zoo (docs/reference/models/model-zoo.md)
2026-10-15 (page last edited)

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