LLM Decoding Throughput on MiniCPM 8B 96K context length 4.1
1,076.3Decoding Throughput (tok/s)
SparDA
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 1,076.3 | |
2026.06 | 939.2 | |
2026.06 | 934.3 | |
2026.06 | 839.5 | |
2026.06 | 752.9 | |
2026.06 | 679.4 | |
2026.06 | 489 | |
2026.06 | 475.6 | |
2026.06 | 401.4 | |
2026.06 | 306 | |
2026.06 | 238.6 | |
2026.06 | 215.5 | |
2026.06 | 185.7 | |
2026.06 | 159 | |
2026.06 | 133.8 | |
2026.06 | 117.9 | |
2026.06 | 86 | |
2026.06 | 64.9 | |
2026.06 | 49.4 |