HPE ProLiant Compute DL380 Gen12 (5x NVIDIA RTX PRO 4500 Blackwell): edge AI benchmarks
Key results
| Workload | Best result | Model · precision | Power · perf/W | Grade · date | Source |
|---|---|---|---|---|---|
| image classification | 94651 FPS batch unknown | MLPerf resnet int8 · TensorRT 10.11.0.33, CUDA 13.0 | unknown | A 2026-04-01 (published) | MLPerf Inference v6.0, closed division, edge suite |
| speech-to-text | 4513 FPS batch unknown | MLPerf whisper fp16 · TensorRT 10.11.0.33, CUDA 13.0 | unknown | A 2026-04-01 (published) | MLPerf Inference v6.0, closed division, edge suite |
| LLM serving (MLPerf datacenter) | 11665 tok/s batch unknown | MLPerf llama3.1-8b fp4 · TensorRT 10.11.0.33, CUDA 13.0 | unknown | A 2026-04-01 (published) | MLPerf Inference v6.0, closed division, data-centre suite |
Best published result per workload, across model sizes. For like-for-like groups, open the per-workload tables below.
Show data — per-workload tables
object detection
No published object detection results for HPE ProLiant Compute DL380 Gen12 (5x NVIDIA RTX PRO 4500 Blackwell) 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 HPE ProLiant Compute DL380 Gen12 (5x NVIDIA RTX PRO 4500 Blackwell) 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 HPE ProLiant Compute DL380 Gen12 (5x NVIDIA RTX PRO 4500 Blackwell) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
image classification
| Like-for-like group | Best result | Model · precision · stack | Grade | Power | Source · date | Rank in group |
|---|---|---|---|---|---|---|
| mid-size CNN · b=unknown | 94651 FPS | MLPerf resnet int8 · TensorRT 10.11.0.33, CUDA 13.0 | A | unknown power n/a | MLPerf Inference v6.0, closed division, edge suite 2026-04-01 (published) | 1 of 41 |
semantic segmentation
No published semantic segmentation results for HPE ProLiant Compute DL380 Gen12 (5x NVIDIA RTX PRO 4500 Blackwell) 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
| Like-for-like group | Best result | Model · precision · stack | Grade | Power | Source · date | Rank in group |
|---|---|---|---|---|---|---|
| unknown · b=unknown | 4513 FPS | MLPerf whisper fp16 · TensorRT 10.11.0.33, CUDA 13.0 | A | unknown power n/a | MLPerf Inference v6.0, closed division, edge suite 2026-04-01 (published) | 33 of 48 |
LLM generation
No published LLM generation results for HPE ProLiant Compute DL380 Gen12 (5x NVIDIA RTX PRO 4500 Blackwell) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
LLM serving (MLPerf datacenter)
| Like-for-like group | Best result | Model · precision · stack | Grade | Power | Source · date | Rank in group |
|---|---|---|---|---|---|---|
| LLM 5–14B · b=unknown | 11665 tok/s | MLPerf llama3.1-8b fp4 · TensorRT 10.11.0.33, CUDA 13.0 | A | unknown power n/a | MLPerf Inference v6.0, closed division, data-centre suite 2026-04-01 (published) | 32 of 48 |
How to read these numbers
Machine-readable: /find.json (see llms.txt); full tables are in “Show data”. Confidence grades: A audited MLPerf closed · B documented third-party · C community · D vendor-published · E estimate. Unknown values are shown as unknown, never estimated. Generated 2026-10-16 from public sources.