Find edge AI hardware
Task graph neural network · model-size class unknown · batch unknown · 5 platforms
✓ Like-for-like: same model (MLPerf rgat), precision (INT8), model-size class and batch.
| Platform | Result | Model · precision · stack | Grade · date | Power | Price | Source |
|---|---|---|---|---|---|---|
| Intel system (Intel Xeon 6980P, CPU only) | 24574 FPS throughput_offline b=unknown | MLPerf rgat INT8 · PyTorch | A 2026-09-16 (published) | unknown no power published | unknown | MLPerf Inference v6.1, closed division, data-centre suite |
| Dell system (Intel Xeon 6980P, CPU only) | 21835 FPS throughput_offline b=unknown | MLPerf rgat INT8 · PyTorch | A 2026-09-16 (published) | unknown no power published | unknown | MLPerf Inference v6.1, closed division, data-centre suite |
| Dell system (Intel Xeon 6787P, CPU only) | 16043 FPS throughput_offline b=unknown | MLPerf rgat INT8 · PyTorch | A 2026-09-16 (published) | unknown no power published | unknown | MLPerf Inference v6.1, closed division, data-centre suite |
| Quanta_Cloud_Technology system (Intel Xeon 6788P, CPU only) | 15633 FPS throughput_offline b=unknown | MLPerf rgat INT8 · PyTorch | A 2026-09-16 (published) | unknown no power published | unknown | MLPerf Inference v6.1, closed division, data-centre suite |
| Cisco system (Intel Xeon 6787P, CPU only) | 14284 FPS throughput_offline b=unknown | MLPerf rgat INT8 · PyTorch | A 2026-04-01 (published) | unknown no power published | unknown | MLPerf Inference v6.0, closed division, data-centre suite |
Confidence: A audited MLPerf closed, B documented third-party, C community, D vendor-published, E estimate. Unknown is never assumed. Other like-for-like groups: unknown, batch not stated (5)