Text Generation on Text model inference M4 Max
525.5Throughput (tok/s)
vllm-mlx
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 525.5 | 1.87 | |
2026.01 | 461.9 | 1.39 | |
2026.01 | 365.8 | - | |
2026.01 | 356.2 | - | |
2026.01 | 350.9 | - | |
2026.01 | 347.1 | - | |
2026.01 | 331.3 | - | |
2026.01 | 281.5 | - | |
2026.01 | 203.6 | 1.31 | |
2026.01 | 174.3 | - | |
2026.01 | 167.5 | - | |
2026.01 | 159 | 1.35 | |
2026.01 | 155.8 | - | |
2026.01 | 152.5 | 1.24 | |
2026.01 | 137.3 | - | |
2026.01 | 128.9 | - | |
2026.01 | 123.2 | - | |
2026.01 | 121.8 | 1.43 | |
2026.01 | 118.2 | - | |
2026.01 | 117 | - | |
2026.01 | 110.3 | - | |
2026.01 | 109.7 | 1.17 | |
2026.01 | 107.4 | - | |
2026.01 | 105.4 | - | |
2026.01 | 101.6 | - | |
2026.01 | 93.3 | 1.21 | |
2026.01 | 89.9 | - | |
2026.01 | 87.1 | - | |
2026.01 | 85.1 | - | |
2026.01 | 79.9 | - | |
2026.01 | 76.9 | - |