Dell Pro Max with GB10 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 all 2 like-for-like comparisons (largest gap: LLM generation, 4.71×).
| Dell Pro Max with GB10 | Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling) | |
|---|---|---|
| Best LLM generation | 97.93 tok/s C 2026-09-22 (page last edited) | 214 tok/s C 2025-05-06 (page last edited) |
| Power | 129 W ● Measured, Whole system | 320 W ● Measured, Whole system |
| Perf / W | 0.762 tok/s/W ● Measured, Whole system | 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 Dell Pro Max with GB10 has published object detection results.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Dell Pro Max with GB10 | 78.73 FPS throughput_offline · b=unknown | MLPerf yolo-95 fp4 · CUDA 13.0 · unknown | A | unknown power not published not published | MLPerf Inference v6.1, closed division, edge suite 2026-09-16 (published) |
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 Dell Pro Max with GB10 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 Dell Pro Max with GB10 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 Dell Pro Max with GB10 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 Dell Pro Max with GB10 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 Dell Pro Max with GB10 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 Dell Pro Max with GB10 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) |
| Dell Pro Max with GB10 | 23.92 tok/s generation_throughput · b=1 | DeepSeek R1 14b as in linked issue (Ollama default tags are 4-bit) · Ollama / llama.cpp (see linked issue) · LLM 5–14B | C | 138 W ● Measured, Whole system reported in result source — Measured, Whole system | Jeff Geerling ai-benchmarks README (Findings tables) 2026-09-22 (page last edited) |
| 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) |
| Dell Pro Max with GB10 | 97.93 tok/s generation_throughput · b=1 | Llama 3.2:3b as in linked issue (Ollama default tags are 4-bit) · Ollama / llama.cpp (see linked issue) · LLM ≤4B | C | 129 W ● Measured, Whole system reported in result source — Measured, Whole system | Jeff Geerling ai-benchmarks README (Findings tables) 2026-09-22 (page last edited) |
Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling) is faster in all 2 like-for-like comparisons (largest gap: LLM generation, 4.71×).
| Dell Pro Max with GB10 | Radxa Oryon O6 Mini ITX Board (as tested by Jeff Geerling) | |
|---|---|---|
| Best LLM generation | 97.93 tok/s C 2026-09-22 (page last edited) | 214 tok/s C 2025-05-06 (page last edited) |
| Power | 129 W ● Measured, Whole system | 320 W ● Measured, Whole system |
| Perf / W | 0.762 tok/s/W ● Measured, Whole system | 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 Dell Pro Max with GB10 has published object detection results.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Dell Pro Max with GB10 | 78.73 FPS throughput_offline · b=unknown | MLPerf yolo-95 fp4 · CUDA 13.0 · unknown | A | unknown power not published not published | MLPerf Inference v6.1, closed division, edge suite 2026-09-16 (published) |
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 Dell Pro Max with GB10 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 Dell Pro Max with GB10 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 Dell Pro Max with GB10 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 Dell Pro Max with GB10 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 Dell Pro Max with GB10 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 Dell Pro Max with GB10 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) |
| Dell Pro Max with GB10 | 23.92 tok/s generation_throughput · b=1 | DeepSeek R1 14b as in linked issue (Ollama default tags are 4-bit) · Ollama / llama.cpp (see linked issue) · LLM 5–14B | C | 138 W ● Measured, Whole system reported in result source — Measured, Whole system | Jeff Geerling ai-benchmarks README (Findings tables) 2026-09-22 (page last edited) |
| 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) |
| Dell Pro Max with GB10 | 97.93 tok/s generation_throughput · b=1 | Llama 3.2:3b as in linked issue (Ollama default tags are 4-bit) · Ollama / llama.cpp (see linked issue) · LLM ≤4B | C | 129 W ● Measured, Whole system reported in result source — Measured, Whole system | Jeff Geerling ai-benchmarks README (Findings tables) 2026-09-22 (page last edited) |
Grades: A audited MLPerf · B third-party · C community · D vendor. How we rank · JSON