Nebius GB300 NVL72 (4x NVIDIA GB300) vs Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling)
Only Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling) has published results here; Nebius GB300 NVL72 (4x NVIDIA GB300) has none for the workloads we track.
| Nebius GB300 NVL72 (4x NVIDIA GB300) | Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling) | |
|---|---|---|
| Best LLM generation | n/a | 214 tok/s C 2025-05-06 (page last edited) |
| Power | n/a | 320 W ● Measured, Whole system |
| Perf / W | n/a | 0.669 tok/s/W ● Measured, Whole system |
| Price | n/a | n/a |
| Workloads with data | 0 of 7 | 1 of 7 |
Best published LLM generation result per platform. n/a = not published; never estimated.
Show data — all workloads, sources and like-for-like groups
object detection
No published object detection results for Nebius GB300 NVL72 (4x NVIDIA GB300) 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.
instance segmentation
No published instance segmentation results for Nebius GB300 NVL72 (4x NVIDIA GB300) 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 Nebius GB300 NVL72 (4x NVIDIA GB300) 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 Nebius GB300 NVL72 (4x NVIDIA GB300) 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 Nebius GB300 NVL72 (4x NVIDIA GB300) 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 Nebius GB300 NVL72 (4x NVIDIA GB300) 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
Only Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling) has published LLM generation results.
| 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) |
Nebius GB300 NVL72 (4x NVIDIA GB300):
No published LLM generation results for Nebius GB300 NVL72 (4x NVIDIA GB300) 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.
Only Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling) has published results here; Nebius GB300 NVL72 (4x NVIDIA GB300) has none for the workloads we track.
| Nebius GB300 NVL72 (4x NVIDIA GB300) | Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling) | |
|---|---|---|
| Best LLM generation | n/a | 214 tok/s C 2025-05-06 (page last edited) |
| Power | n/a | 320 W ● Measured, Whole system |
| Perf / W | n/a | 0.669 tok/s/W ● Measured, Whole system |
| Price | n/a | n/a |
| Workloads with data | 0 of 7 | 1 of 7 |
Best published LLM generation result per platform. n/a = not published; never estimated.
Show data — all workloads, sources and like-for-like groups
object detection
No published object detection results for Nebius GB300 NVL72 (4x NVIDIA GB300) 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.
instance segmentation
No published instance segmentation results for Nebius GB300 NVL72 (4x NVIDIA GB300) 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 Nebius GB300 NVL72 (4x NVIDIA GB300) 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 Nebius GB300 NVL72 (4x NVIDIA GB300) 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 Nebius GB300 NVL72 (4x NVIDIA GB300) 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 Nebius GB300 NVL72 (4x NVIDIA GB300) 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
Only Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling) has published LLM generation results.
| 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) |
Nebius GB300 NVL72 (4x NVIDIA GB300):
No published LLM generation results for Nebius GB300 NVL72 (4x NVIDIA GB300) 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.
Grades: A audited MLPerf · B third-party · C community · D vendor. How we rank · JSON