LLM Inference on WildChat
75.17RPS (Requests/s)v1
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| v1GPU=H200, Model=Gemma-3-1B-IT2026.05 | 75.17 | — | — | — | |
| EB(k^*)GPU=H200, Model=Gemma-3-1B-IT2026.05 | 74.05 | — | — | -1.5 | |
| v0GPU=H200, Model=Gemma-3-1B-IT2026.05 | 71.82 | — | — | — | |
| EB(k^*)GPU=RTX PRO 6000, Model=Gemma-3-1B-IT2026.05 | 56.26 | — | — | 5.4 | |
| v0GPU=RTX PRO 6000, Model=Gemma-3-1B-IT2026.05 | 55.97 | — | — | — | |
| v1GPU=RTX PRO 6000, Model=Gemma-3-1B-IT2026.05 | 53.36 | — | — | — | |
| EB(k*)GPU=B3002026.05 | 52.34 | 2.87 | 22.12 | — | |
| v1GPU=B3002026.05 | 50.47 | 2.08 | 24 | — | |
| EB(k*)GPU=L40S2026.05 | 14.7 | 92.16 | 138.16 | — | |
| v1GPU=L40S2026.05 | 10.36 | 132.47 | 189.7 | — | |
| v0GPU=L40S2026.05 | 4.14 | 157.21 | 171.02 | — |