NVIDIA DGX Spark vs Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling)
Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling) is faster in the only like-for-like comparison (largest gap: LLM generation, 1.87×).
| NVIDIA DGX Spark | Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling) | |
|---|---|---|
| Best LLM generation | 191 tok/s C 2026-07-21 (page last edited) | 214 tok/s C 2025-05-06 (page last edited) |
| Power | 140 W Chip TDP, Accelerator only, host not included | 320 W ● Measured, Whole system |
| Perf / W | 1.37 tok/s/W Chip TDP, Accelerator only, host not included | 0.669 tok/s/W ● Measured, Whole system |
| Price | $6950 list | 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 NVIDIA DGX Spark has published object detection results.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| NVIDIA DGX Spark | 990 FPS inference_time · b=1 | YOLO11n FP16 · Ultralytics TensorRT · nano (YOLO-n) | B | 140 W Chip TDP, Accelerator only, host not included reported in result source — Chip TDP, Accelerator only, host not included | Ultralytics documentation (benchmark table) 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 NVIDIA DGX Spark 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 NVIDIA DGX Spark 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 NVIDIA DGX Spark 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 NVIDIA DGX Spark 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 NVIDIA DGX Spark 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 NVIDIA DGX Spark 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
| 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) |
| NVIDIA DGX Spark | 60.39 tok/s tg128 · b=1 | Llama 2 7B Q4_0 · llama.cpp Vulkan (FA on, commit 657e011) · LLM 5–14B | C | unknown power not published not published | llama.cpp discussion #10879 Vulkan scoreboard (via GitHub API) 2026-10-10 (page last edited) |
Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling) is faster in the only like-for-like comparison (largest gap: LLM generation, 1.87×).
| NVIDIA DGX Spark | Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling) | |
|---|---|---|
| Best LLM generation | 191 tok/s C 2026-07-21 (page last edited) | 214 tok/s C 2025-05-06 (page last edited) |
| Power | 140 W Chip TDP, Accelerator only, host not included | 320 W ● Measured, Whole system |
| Perf / W | 1.37 tok/s/W Chip TDP, Accelerator only, host not included | 0.669 tok/s/W ● Measured, Whole system |
| Price | $6950 list | 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 NVIDIA DGX Spark has published object detection results.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| NVIDIA DGX Spark | 990 FPS inference_time · b=1 | YOLO11n FP16 · Ultralytics TensorRT · nano (YOLO-n) | B | 140 W Chip TDP, Accelerator only, host not included reported in result source — Chip TDP, Accelerator only, host not included | Ultralytics documentation (benchmark table) 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 NVIDIA DGX Spark 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 NVIDIA DGX Spark 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 NVIDIA DGX Spark 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 NVIDIA DGX Spark 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 NVIDIA DGX Spark 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 NVIDIA DGX Spark 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
| 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) |
| NVIDIA DGX Spark | 60.39 tok/s tg128 · b=1 | Llama 2 7B Q4_0 · llama.cpp Vulkan (FA on, commit 657e011) · LLM 5–14B | C | unknown power not published not published | llama.cpp discussion #10879 Vulkan scoreboard (via GitHub API) 2026-10-10 (page last edited) |
Grades: A audited MLPerf · B third-party · C community · D vendor. How we rank · JSON