Intel Core Ultra 7 258V (Lunar Lake) vs Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling)

Macro photograph of the Intel Lunar Lake (Core Ultra 200V) processor tiles — Intel Core Ultra 9 288V (Lunar Lake) die tiles, macro photo; the 258V uses the same Lunar Lake design. Photo: FritzchensFritz, CC0, via Wikimedia Commons.

(independent test)independent test systemNo licensed photo yet

Showing the newest results per platform and source. 11 superseded older results are hidden.Showing all results, including 11 superseded by newer results from the same source.

Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling) is faster in all 2 like-for-like comparisons (largest gap: LLM generation, 1.59×).

	Intel Core Ultra 7 258V (Lunar Lake)	Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling)
Best LLM generation	200 tok/s D 2026-10-01 (published)	214 tok/s C 2025-05-06 (page last edited)
Power	37.00 W Chip TDP, Accelerator only, host not included, max of range 8-37 W	320 W ● Measured, Whole system
Perf / W	5.41 tok/s/W Chip TDP, Accelerator only, host not included, max of range 8-37 W	0.669 tok/s/W ● Measured, Whole system
Price	n/a	n/a
Workloads with data	2 of 7	1 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

Only Intel Core Ultra 7 258V (Lunar Lake) has published object detection results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Intel Core Ultra 7 258V (Lunar Lake)	300 FPS inference_time · b=1	YOLO26n FP32 · Ultralytics + OpenVINO 2026.2.1 · nano (YOLO-n)	C	37.00 W Chip TDP, Accelerator only, host not included, max of range 8-37 W reported in result source — Chip TDP, Accelerator only, host not included, max of range 8-37 W	Ultralytics documentation: Intel OpenVINO integration benchmark 2026-09-27 (page last edited)

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

◌

No published object detection results for Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling) or Intel Core Ultra 7 258V (Lunar Lake) 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 Intel Core Ultra 7 258V (Lunar Lake) or 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 Intel Core Ultra 7 258V (Lunar Lake) or 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 Intel Core Ultra 7 258V (Lunar Lake) or 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 Intel Core Ultra 7 258V (Lunar Lake) or 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 Intel Core Ultra 7 258V (Lunar Lake) or 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: model-size class LLM ≤4B, batch 1. Model, precision and stack may still differ.

Platform	Result	Model · precision · stack	Grade	Power	Source
Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling)	214 tok/s generation_throughput · b=1	deepseek-r1:1.5b Ollama default tag (4-bit unless tag says otherwise) · Ollama (geerlingguy/ollama-benchmark) · LLM ≤4B	C	320 W ● Measured, Whole system reported in result source — Measured, Whole system	Jeff Geerling ai-benchmarks issue results (comments) 2025-05-06 (page last edited)
Intel Core Ultra 7 258V (Lunar Lake)	135 tok/s 2nd-token throughput, input 32 tokens · b=1	minicpm4-0.5b INT4-MIXED · OpenVINO 2026.4.1 GenAI · LLM ≤4B	D	37.00 W Chip TDP, Accelerator only, host not included, max of range 8-37 W reported in result source — Chip TDP, Accelerator only, host not included, max of range 8-37 W	OpenVINO official LLM benchmarks (llm_models_7-258V.csv) 2026-10-01 (published)

✓ Like-for-like: model-size class LLM 5–14B, batch 1. Model, precision and stack may still differ.

Platform	Result	Model · precision · stack	Grade	Power	Source
Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling)	113 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	471 W ● Measured, Whole system reported in result source — Measured, Whole system	Jeff Geerling ai-benchmarks issue results (comments) 2025-05-06 (page last edited)
Intel Core Ultra 7 258V (Lunar Lake)	89.29 tok/s 2nd-token throughput, input 32 tokens · b=1	lfm2-8b-a1b INT4-MIXED · OpenVINO 2026.4.1 GenAI · LLM 5–14B	D	37.00 W Chip TDP, Accelerator only, host not included, max of range 8-37 W reported in result source — Chip TDP, Accelerator only, host not included, max of range 8-37 W	OpenVINO official LLM benchmarks (llm_models_7-258V.csv) 2026-10-01 (published)