Runtime latency, throughput, and scaling data across reference platforms. All measurements at v0.9.x on default configuration unless noted.
End-to-end scene contract latency from sensor frame to validated output. Measured at 30 fps per camera, full OSTVAL™ pipeline enabled.
| Platform | Cameras | FPS | Latency |
|---|---|---|---|
| Raspberry P5 + RK1820 | 2 | 30 | 45 ms |
| RK3588 + RK1828 | 8 | 30 | 30 ms |
| Jetson Orin | 4 | 30 | 40 ms |
| RTX 3070 | 6 | 30 | 12 ms |
Scene generation throughput Projected · (v2.0 benchmark run pending) on RK3588 + Rk1828 · 4 cameras · 30 fps. Objects and events per second at sustained load.
| Metric | Value |
|---|---|
| Objects / sec | 520 |
| Events / sec | 138 |
| Memory usage | 256 MB |
Fusion pipeline latency scaling across camera count. Reference platform: RK3588 + RK1828 · 30 fps per camera.
| Cameras | Latency |
|---|---|
| 1 camera | 12 ms |
| 2 cameras | 15 ms |
| 4 cameras | 21 ms |
| 8 cameras | 38 ms |
Storage impact of the VAOS Memory Engine over time. Reference platform: RK3588 + RK1828 · 4 cameras · default retention policy.
| Duration | Storage impact |
|---|---|
| 1 hour | 12 MB |
| 24 hours | 280 MB |
| 7 days | 1.9 GB |
| 30 days | 7.4 GB |
Inference latency per scene contract on RK3588 + RK1828 NPU. Lower is better. Measured at single-scene, no batching.
| Model | Inference latency |
|---|---|
| Gemma 2B | ~3s |
| Gemma 4B | ~5s |
| Qwen 3 | ~6s |
benchmarks/. Community contributions welcome — see the contributors guide. (Some values are projected engineering targets based on current VAOS v2.0 runtime assumptions. Final measured results will be published with reproducible benchmark scripts and hardware configuration files)