Inference Efficiency on Text-only tasks vLLM NVIDIA RTX 4090
212.3Throughput (tokens/s)MiniCPM-o 4.5
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MiniCPM-o 4.5Dtype=INT42026.04 | 212.3 | 11 | |
| MiniCPM-o 4.5Dtype=BF162026.04 | 154.3 | 19 | |
| Qwen3-Omni-30B-A3BDtype=INT42026.04 | 147.8 | 20 |