Recommendation inference — user-item scoring queries per second per GPU. · DLRM-v2 · collaborative filtering · v4.1 / v5.0 / v5.1 / v6.0 / v6.1 · on-demand pricing
| GPU | Scenario | samp/s per GPU | |
|---|---|---|---|
| NVIDIA H200-SXM-141GB | Offline | 80,470 samp/s | |
| NVIDIA H100-SXM-80GB | Offline | 75,264 samp/s | |
| NVIDIA H200-SXM-141GB | Server | 73,145 samp/s | |
| NVIDIA H100-SXM-80GB | Server | 69,513 samp/s |
| Provider | GPU | Scenario | Price | samp/$ | |
|---|---|---|---|---|---|
| Lambda Labs | NVIDIA H200-SXM-141GB | Offline | $2.29/GPU·hr 48m ago | 126,502,271 | |
| Lambda Labs | NVIDIA H200-SXM-141GB | Server | $2.29/GPU·hr 48m ago | 114,988,541 | |
| Hyperstack | NVIDIA H200-SXM-141GB | Offline | $2.79/GPU·hr 48m ago | 103,831,613 | |
| Hyperstack | NVIDIA H100-SXM-80GB | Offline | $2.72/GPU·hr 48m ago | 99,613,456 | |
| Hyperstack | NVIDIA H200-SXM-141GB | Server | $2.79/GPU·hr 48m ago | 94,381,276 | |
| Hyperstack | NVIDIA H100-SXM-80GB | Server | $2.72/GPU·hr 48m ago | 92,001,994 | |
| RunPod | NVIDIA H100-SXM-80GB | Offline | $3.99/GPU·hr 48m ago | 67,906,917 | |
| Lambda Labs | NVIDIA H100-SXM-80GB | Offline | $3.99/GPU·hr 48m ago | 67,906,917 | |
| DigitalOcean | NVIDIA H200-SXM-141GB | Offline | $4.47/GPU·hr 48m ago | 64,807,651 | |
| RunPod | NVIDIA H100-SXM-80GB | Server | $3.99/GPU·hr 48m ago | 62,718,151 | |
| Lambda Labs | NVIDIA H100-SXM-80GB | Server | $3.99/GPU·hr 48m ago | 62,718,151 | |
| DigitalOcean | NVIDIA H100-SXM-80GB | Offline | $4.41/GPU·hr 48m ago | 61,439,592 | |
| Crusoe | NVIDIA H100-SXM-80GB | Offline | $4.50/GPU·hr 48m ago | 60,210,800 | |
| Nebius | NVIDIA H100-SXM-80GB | Offline | $4.50/GPU·hr 48m ago | 60,210,800 | |
| DigitalOcean | NVIDIA H200-SXM-141GB | Server | $4.47/GPU·hr 48m ago | 58,909,118 | |
| DigitalOcean | NVIDIA H100-SXM-80GB | Server | $4.41/GPU·hr 48m ago | 56,744,994 | |
| Crusoe | NVIDIA H100-SXM-80GB | Server | $4.50/GPU·hr 48m ago | 55,610,094 | |
| Nebius | NVIDIA H100-SXM-80GB | Server | $4.50/GPU·hr 48m ago | 55,610,094 | |
| RunPod | NVIDIA H200-SXM-141GB | Offline | $5.29/GPU·hr 48m ago | 54,761,853 | |
| Crusoe | NVIDIA H200-SXM-141GB | Offline | $5.40/GPU·hr 48m ago | 53,646,333 | |
| Nebius | NVIDIA H200-SXM-141GB | Offline | $5.40/GPU·hr 48m ago | 53,646,333 | |
| RunPod | NVIDIA H200-SXM-141GB | Server | $5.29/GPU·hr 48m ago | 49,777,648 | |
| Crusoe | NVIDIA H200-SXM-141GB | Server | $5.40/GPU·hr 48m ago | 48,763,659 | |
| Nebius | NVIDIA H200-SXM-141GB | Server | $5.40/GPU·hr 48m ago | 48,763,659 | |
| CoreWeave | NVIDIA H200-SXM-141GB | Offline | $6.31/GPU·hr 48m ago | 45,909,699 | |
| CoreWeave | NVIDIA H100-SXM-80GB | Offline | $6.16/GPU·hr 48m ago | 43,985,162 | |
| CoreWeave | NVIDIA H200-SXM-141GB | Server | $6.31/GPU·hr 48m ago | 41,731,182 | |
| CoreWeave | NVIDIA H100-SXM-80GB | Server | $6.16/GPU·hr 48m ago | 40,624,257 | |
| OCI | NVIDIA H200-SXM-141GB | Offline | $10.00/GPU·hr 48m ago | 28,969,020 | |
| Azure (eastus2) | NVIDIA H200-SXM-141GB | Offline | $10.60/GPU·hr 48m ago | 27,329,264 | |
| GCP (us-central1) | NVIDIA H200-SXM-141GB | Offline | $10.84/GPU·hr 48m ago | 26,711,893 | |
| OCI | NVIDIA H200-SXM-141GB | Server | $10.00/GPU·hr 48m ago | 26,332,376 | |
| OCI | NVIDIA H100-SXM-80GB | Offline | $10.75/GPU·hr 48m ago | 25,204,521 | |
| Azure (eastus2) | NVIDIA H200-SXM-141GB | Server | $10.60/GPU·hr 48m ago | 24,841,864 | |
| GCP (us-central1) | NVIDIA H200-SXM-141GB | Server | $10.84/GPU·hr 48m ago | 24,280,684 | |
| GCP (us-central1) | NVIDIA H100-SXM-80GB | Offline | $11.53/GPU·hr 48m ago | 23,506,003 | |
| OCI | NVIDIA H100-SXM-80GB | Server | $10.75/GPU·hr 48m ago | 23,278,644 | |
| AWS (us-east-1) | NVIDIA H100-SXM-80GB | Offline | $12.29/GPU·hr 48m ago | 22,046,265 | |
| Azure (eastus) | NVIDIA H100-SXM-80GB | Offline | $12.29/GPU·hr 48m ago | 22,046,265 | |
| Azure (eastus2) | NVIDIA H100-SXM-80GB | Offline | $12.29/GPU·hr 48m ago | 22,046,265 | |
| GCP (us-central1) | NVIDIA H100-SXM-80GB | Server | $11.53/GPU·hr 48m ago | 21,709,909 | |
| AWS (us-east-1) | NVIDIA H100-SXM-80GB | Server | $12.29/GPU·hr 48m ago | 20,361,711 | |
| Azure (eastus) | NVIDIA H100-SXM-80GB | Server | $12.29/GPU·hr 48m ago | 20,361,711 | |
| Azure (eastus2) | NVIDIA H100-SXM-80GB | Server | $12.29/GPU·hr 48m ago | 20,361,711 |