Measured over the last 30 days
- Models Tracked
- 7
- Avg Tokens / Second
- 16.96
- Avg Time to First Token (ms)
- 20375.71
- Last Updated
- Oct 17, 2026
All mancer models
7 live · one row per model · fastest first| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| MythoMax 13B | 50.10 | 48.30 | 52.00 | 550.00 |
| ReMM SLERP 13B | 34.30 | 34.30 | 34.30 | 570.00 |
| Magnum v4 72B | 15.40 | 15.40 | 15.40 | 1030.00 |
| gpt-oss-120b | 9.91 | 7.98 | 11.80 | 5180.00 |
| DeepSeek V4 Flash 0423 | 5.35 | 2.73 | 11.30 | 14400.00 |
| DeepSeek V4 Flash 0731 | 2.98 | 1.96 | 4.00 | 22500.00 |
| GLM 4.7 | 0.65 | 0.59 | 0.70 | 98400.00 |
Frequently Asked Questions
Which mancer model is fastest?
Based on recent tests, MythoMax 13B shows the highest average throughput among tracked mancer models.
How many recent measurements feed this dashboard?
This provider summary aggregates 878 individual prompts measured across 850 monitoring runs over the past month.