Find edge AI hardware
Task image/video generation · model-size class unknown · batch unknown · 16 platforms
Not like-for-like across groups: same model-size class and batch, but 5 different model/precision combinations. Compare within a group; each group is sorted by result.
MLPerf wan-2.2-t2v-a14b · fp8 (7)
| Platform | Result | Model · precision · stack | Grade · date | Power | Price | Source |
|---|---|---|---|---|---|---|
| NVIDIA GB300 NVL72 (4x NVIDIA GB300) | 0.655 FPS throughput_offline b=unknown | MLPerf wan-2.2-t2v-a14b fp8 · 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 2026-09-16 (published) | unknown no power published | unknown | MLPerf Inference v6.1, closed division, data-centre suite |
| Dell PowerEdge XE9712 (4x NVIDIA GB300) | 0.646 FPS throughput_offline b=unknown | MLPerf wan-2.2-t2v-a14b fp8 · 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 2026-09-16 (published) | unknown no power published | unknown | MLPerf Inference v6.1, closed division, data-centre suite |
| NVIDIA GB200 NVL72 (4x NVIDIA GB200) | 0.496 FPS throughput_offline b=unknown | MLPerf wan-2.2-t2v-a14b fp8 · 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 2026-09-16 (published) | unknown no power published | unknown | MLPerf Inference v6.1, closed division, data-centre suite |
| G894-AD3-AAX7 (8x NVIDIA B300-SXM-270GB) | 0.0629 FPS throughput_offline b=unknown | MLPerf wan-2.2-t2v-a14b fp8 · 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 2026-09-16 (published) | unknown no power published | unknown | MLPerf Inference v6.1, closed division, data-centre suite |
| G894-ZD3-AAX7 (8x NVIDIA B300-SXM-270GB) | 0.0625 FPS throughput_offline b=unknown | MLPerf wan-2.2-t2v-a14b fp8 · 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 2026-09-16 (published) | unknown no power published | unknown | MLPerf Inference v6.1, closed division, data-centre suite |
| NVIDIA DGX B300 (8x NVIDIA B300-SXM-270GB) | 0.0622 FPS throughput_offline b=unknown | MLPerf wan-2.2-t2v-a14b fp8 · 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 2026-09-16 (published) | unknown no power published | unknown | MLPerf Inference v6.1, closed division, data-centre suite |
| Cisco UCS C880A M8 (8x NVIDIA B300-SXM-270GB) | 0.0613 FPS throughput_offline b=unknown | MLPerf wan-2.2-t2v-a14b fp8 · TensorRT 10.14, CUDA 13.1 | A 2026-09-16 (published) | unknown no power published | unknown | MLPerf Inference v6.1, closed division, data-centre suite |
MLPerf stable-diffusion-xl · per MLPerf v4.0 submission (1)
| Platform | Result | Model · precision · stack | Grade · date | Power | Price | Source |
|---|---|---|---|---|---|---|
| NVIDIA Jetson AGX Orin 64GB | 0.0800 FPS latency_single_stream b=unknown | MLPerf stable-diffusion-xl per MLPerf v4.0 submission · TensorRT 9.0.1, JetPack 5.1.1, CUDA 11.4 | D 2024-03-27 (published) | 65.00 W platform spec envelope (not measured with this result) | $3499 | NVIDIA Jetson Benchmarks (MLPerf v4.0 results table) |
MLPerf wan-2.2-t2v-a14b · bf16, fp8, fp4 (5)
| Platform | Result | Model · precision · stack | Grade · date | Power | Price | Source |
|---|---|---|---|---|---|---|
| smci355-ccs-aus-m13-13 (8x AMD Instinct MI355X 288GB HBM3e) | 0.0731 FPS throughput_offline b=unknown | MLPerf wan-2.2-t2v-a14b bf16, fp8, fp4 · 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 |
| HPE ProLiant Compute XD685 (8x AMD Instinct MI355X 288GB HBM3e) | 0.0707 FPS throughput_offline b=unknown | MLPerf wan-2.2-t2v-a14b bf16, fp8, fp4 · 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 |
| 8xMI355X_2xEPYC_9575F (8x AMD Instinct MI355X 288GB HBM3e) | 0.0706 FPS throughput_offline b=unknown | MLPerf wan-2.2-t2v-a14b bf16, fp8, fp4 · 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 |
| Quanta Grand Teton 1.5 MI350 (8x AMD Instinct MI350X 288GB HBM3e) | 0.0565 FPS throughput_offline b=unknown | MLPerf wan-2.2-t2v-a14b bf16, fp8, fp4 · xDiT, xfuser 0.4.5, PyTorch 2.9.1+gitff65f5b, ROCm 7.13.0 | A 2026-09-16 (published) | unknown no power published | unknown | MLPerf Inference v6.1, closed division, data-centre suite |
| XE7745_8xMI350P_2xEPYC_9455 (8x AMD Instinct MI350P) | 0.0346 FPS throughput_offline b=unknown | MLPerf wan-2.2-t2v-a14b bf16, fp8, fp4 · 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 |
MLPerf wan-2.2-t2v-a14b · fp32 (2)
| Platform | Result | Model · precision · stack | Grade · date | Power | Price | Source |
|---|---|---|---|---|---|---|
| G894-SD3-AAX7 (8x NVIDIA B300-SXM-270GB) | 0.0583 FPS throughput_offline b=unknown | MLPerf wan-2.2-t2v-a14b fp32 · 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 |
| NVIDIA DGX B200 (8x NVIDIA B200-SXM-180GB) | 0.0464 FPS throughput_offline b=unknown | MLPerf wan-2.2-t2v-a14b fp32 · 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 |
MLPerf wan-2.2-t2v-a14b · bfloat16 (1)
| Platform | Result | Model · precision · stack | Grade · date | Power | Price | Source |
|---|---|---|---|---|---|---|
| HPE Cray XD670 (8x NVIDIA H200-SXM-141GB) | 0.0241 FPS throughput_offline b=unknown | MLPerf wan-2.2-t2v-a14b bfloat16 · KISS-V: Krai Inference Serving Solution for Video (Fast Mode) | B 2026-04-01 (published) | unknown no power published | unknown | MLPerf Inference v6.0, open 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 (16)