Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling): edge AI benchmarks

(independent test)independent test systemNo licensed photo yet

Vendor (independent test)Form factor independent test systemCompute as described in commentIndicative price unknownPower envelope unknownPublished rows 17

Independent test Jeff Geerling

Showing the newest results per platform and source. 11 superseded older results are hidden.Showing all results, including 11 superseded by newer results from the same source.

Key results

How to read power: results are compared only within the same model. By efficiency ranks only results whose source publishes a power figure; By speed ranks every result. Measured = measured for this workload. Vendor-measured (typical/avg) = the vendor’s own measurement at typical or average load, not an independent test and not a maximum, so fps/W looks better than at max TDP. Chip, Module or Board TDP = the vendor’s published maximum, not measured. Typical power, not max TDP = only a typical figure is published, so fps/W looks better than at full load. Scope says what the watts cover: Accelerator only (host not included), Module, or Whole system. Max of range = top of a published range, so fps/W is a floor (≥). “— not published” = the source gives no power; we never estimate one.

Published results for Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling), per workload and model, with rank among boards on the same model
Workload	Model · precision	Result	Power	Perf/W	Rank on this model	Grade · date	Source
LLM generation	deepseek-r1:14bOllama default tag (4-bit unless tag says otherwise) · batch 1	64.58 tok/s	465 WWhole system Measured	0.139● Measured · Whole system	not in the default fps/W ranking #1 of 15 by speed	C 2025-05-06 (page last edited)	Jeff Geerling ai-benchmarks issue results (comments)ai-benchmarks README @ 2f56f19
	deepseek-r1:1.5bOllama default tag (4-bit unless tag says otherwise) · batch 1	214 tok/s	320 WWhole system Measured	0.669● Measured · Whole system	not in the default fps/W ranking #1 of 4 by speed	C 2025-05-06 (page last edited)	Jeff Geerling ai-benchmarks issue results (comments)ai-benchmarks README @ 2f56f19
	deepseek-r1:8bOllama default tag (4-bit unless tag says otherwise) · batch 1	112 tok/s	466 WWhole system Measured	0.241● Measured · Whole system	not in the default fps/W ranking #1 of 2 by speed	C 2025-05-06 (page last edited)	Jeff Geerling ai-benchmarks issue results (comments)ai-benchmarks README @ 2f56f19

Ranks compare this board only with boards running the same model. Up to three models per workload; open a rank to see the full same-model table.

Show data — per-workload tables

object detection

◌

No published object detection results for Radxa Oryon O6 Mini ITX Board (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 Radxa Oryon O6 Mini ITX Board (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 Radxa Oryon O6 Mini ITX Board (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 Radxa Oryon O6 Mini ITX Board (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 Radxa Oryon O6 Mini ITX Board (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 Radxa Oryon O6 Mini ITX Board (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 group	Best result	Model · precision · stack	Grade	Power	Source · date	Rank in group
LLM ≤4B · b=1	214 tok/s	deepseek-r1:1.5b Ollama default tag (4-bit unless tag says otherwise) · Ollama (geerlingguy/ollama-benchmark)	C	320 W ● Measured, Whole system	Jeff Geerling ai-benchmarks issue results (comments) 2025-05-06 (page last edited)	9 of 80
LLM 5–14B · b=1	113 tok/s	llama3.1:8b Ollama default tag (4-bit unless tag says otherwise) · Ollama (geerlingguy/ollama-benchmark)	C	471 W ● Measured, Whole system	Jeff Geerling ai-benchmarks issue results (comments) 2025-05-06 (page last edited)	4 of 66