LLM Inference Throughput on LongBench
96.93Throughput (RPS)EB(k^*)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| EB(k^*)GPU=H200, Model=Gemma-3-1B-IT2026.05 | 96.93 | 4.4 | |
| v1GPU=H200, Model=Gemma-3-1B-IT2026.05 | 92.84 | — | |
| v0GPU=H200, Model=Gemma-3-1B-IT2026.05 | 92.74 | — | |
| EB(k^*)GPU=RTX PRO 6000, Model=Gemma-3-1B-IT2026.05 | 55.31 | 0.4 | |
| v1GPU=RTX PRO 6000, Model=Gemma-3-1B-IT2026.05 | 55.08 | — | |
| v0GPU=RTX PRO 6000, Model=Gemma-3-1B-IT2026.05 | 51.09 | — |