DC-ROMA RISC-V Mainboard II (as tested by Jeff Geerling): edge AI benchmarks
- Independent test Jeff Geerling
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.
| Workload | Model · precision | Result | Power | Perf/W | Rank on this model | Grade · date | Source |
|---|---|---|---|---|---|---|---|
| LLM generation | deepseek-r1:7bOllama default tag (4-bit unless tag says otherwise) · batch 1 | 2.53 tok/s | — not published | not ranked by efficiency (no power published) #3 of 3 by speed | C 2025-10-24 (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 DC-ROMA RISC-V Mainboard II (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 DC-ROMA RISC-V Mainboard II (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 DC-ROMA RISC-V Mainboard II (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 DC-ROMA RISC-V Mainboard II (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 DC-ROMA RISC-V Mainboard II (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 DC-ROMA RISC-V Mainboard II (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 5–14B · b=1 | 2.53 tok/s | deepseek-r1:7b Ollama default tag (4-bit unless tag says otherwise) · Ollama (geerlingguy/ollama-benchmark) | C | unknown power not published | Jeff Geerling ai-benchmarks issue results (comments) 2025-10-24 (page last edited) | 61 of 66 |
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.
| Workload | Model · precision | Result | Power | Perf/W | Rank on this model | Grade · date | Source |
|---|---|---|---|---|---|---|---|
| LLM generation | deepseek-r1:1.5bOllama default tag (4-bit unless tag says otherwise) · batch 1 | 0.590 tok/s | — not published | not ranked by efficiency (no power published) #4 of 5 by speed | C 2025-10-17 (page last edited) | Jeff Geerling ai-benchmarks issue results (comments)ai-benchmarks README @ 2f56f19 | |
| deepseek-r1:7bOllama default tag (4-bit unless tag says otherwise) · batch 1 | 2.53 tok/s | — not published | not ranked by efficiency (no power published) #3 of 3 by speed | C 2025-10-24 (page last edited) | Jeff Geerling ai-benchmarks issue results (comments)ai-benchmarks README @ 2f56f19 | ||
| llama3.2:3bOllama default tag (4-bit unless tag says otherwise) · batch 1 | 0.310 tok/s | — not published | not ranked by efficiency (no power published) #33 of 35 by speed | C 2025-10-17 (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 DC-ROMA RISC-V Mainboard II (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 DC-ROMA RISC-V Mainboard II (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 DC-ROMA RISC-V Mainboard II (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 DC-ROMA RISC-V Mainboard II (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 DC-ROMA RISC-V Mainboard II (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 DC-ROMA RISC-V Mainboard II (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 | 0.590 tok/s | deepseek-r1:1.5b Ollama default tag (4-bit unless tag says otherwise) · Ollama (geerlingguy/ollama-benchmark) | C | unknown power not published | Jeff Geerling ai-benchmarks issue results (comments) 2025-10-17 (page last edited) | 78 of 81 |
| LLM 5–14B · b=1 | 2.53 tok/s | deepseek-r1:7b Ollama default tag (4-bit unless tag says otherwise) · Ollama (geerlingguy/ollama-benchmark) | C | unknown power not published | Jeff Geerling ai-benchmarks issue results (comments) 2025-10-24 (page last edited) | 61 of 66 |
Grades: A audited MLPerf · B third-party · C community · D vendor. How we rank · JSON