LLM Inference on Qwen 1.5B Instruct 2.5
155.3Throughput (tok/s)
CUDA (eager, RTX 5090)
Updated 13d ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.02 | 155.3 | 154.9 | 0.6 | - | 1 | |
2026.02 | 20.6 | 20.4 | 2.9 | - | 0.13 | |
| 17.9 | 17.7 | 3.8 | 51.3 | 0.12 | ||
| 10.4 | 10.4 | 0.9 | 87.9 | 0.07 |
CUDA (eager, RTX 5090)
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.02 | 155.3 | 154.9 | 0.6 | - | 1 | |
2026.02 | 20.6 | 20.4 | 2.9 | - | 0.13 | |
| 17.9 | 17.7 | 3.8 | 51.3 | 0.12 | ||
| 10.4 | 10.4 | 0.9 | 87.9 | 0.07 |