Find edge AI hardware
Task recommendation · model-size class unknown · batch unknown · 7 platforms
Not like-for-like across groups: same model-size class and batch, but 3 different model/precision combinations. Compare within a group; each group is sorted by result.
MLPerf dlrm-v3 · fp16 (3)
| Platform | Result | Model · precision · stack | Grade · date | Power | Price | Source |
|---|---|---|---|---|---|---|
| NVIDIA GB200 NVL72 (4x NVIDIA GB200) | 104637 FPS throughput_offline b=unknown | MLPerf dlrm-v3 fp16 · TensorRT 10.14, CUDA 13.1, cuDNN 9.17, TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentM | A 2026-04-01 (published) | unknown no power published | unknown | MLPerf Inference v6.0, closed division, data-centre suite |
| Camarero PDI200A2HG-810 (8x NVIDIA B200-SXM-180GB) | 10737 FPS throughput_offline b=unknown | MLPerf dlrm-v3 fp16 · TensorRT 10.14, CUDA 13.1, cuDNN 9.17, TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentM | A 2026-04-01 (published) | unknown no power published | unknown | MLPerf Inference v6.0, closed division, data-centre suite |
| NVIDIA DGX B200 (8x NVIDIA B200-SXM-180GB) | 10447 FPS throughput_offline b=unknown | MLPerf dlrm-v3 fp16 · TensorRT 10.14, CUDA 13.1 | A 2026-04-01 (published) | unknown no power published | unknown | MLPerf Inference v6.0, closed division, data-centre suite |
MLPerf dlrm-v3 · fp16,bf16,fp8 (3)
| Platform | Result | Model · precision · stack | Grade · date | Power | Price | Source |
|---|---|---|---|---|---|---|
| 8xMI355X_2xEPYC_9575F (8x AMD Instinct MI355X) | 16363 FPS throughput_offline b=unknown | MLPerf dlrm-v3 fp16,bf16,fp8 · PyTorch 2.10.0+rocm7.2.3.git1a270074, Triton 3.6.0, ROCm 7.2.3 | B 2026-09-16 (published) | unknown no power published | unknown | MLPerf Inference v6.1, open division, data-centre suite |
| smci355-ccs-aus-m13-13 (8x AMD Instinct MI355X 288GB HBM3e) | 13028 FPS throughput_offline b=unknown | MLPerf dlrm-v3 fp16,bf16,fp8 · PyTorch 2.10.0+git8514f05, ROCm 7.2.2 | A 2026-09-16 (published) | unknown no power published | unknown | MLPerf Inference v6.1, closed division, data-centre suite |
| 8xMI350X_2xEPYC_9575F (8x AMD Instinct MI350X 288GB HBM3e) | 10891 FPS throughput_offline b=unknown | MLPerf dlrm-v3 fp16,bf16,fp8 · PyTorch 2.10.0+rocm7.2.3, Triton 3.6.0, ROCm 7.2.3 | A 2026-09-16 (published) | unknown no power published | unknown | MLPerf Inference v6.1, closed division, data-centre suite |
MLPerf dlrm-v3 · int8,bf16 (1)
| Platform | Result | Model · precision · stack | Grade · date | Power | Price | Source |
|---|---|---|---|---|---|---|
| XE7745_8xMI350P_2xEPYC_9455 (8x AMD Instinct MI350P) | 4838 FPS throughput_offline b=unknown | MLPerf dlrm-v3 int8,bf16 · vLLM 0.22.0, PyTorch 2.10.0, ROCm 7.2.2 | A 2026-09-16 (published) | unknown no power published | unknown | MLPerf Inference v6.1, 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 (7)