Measured over the last 30 days
- Models Tracked
- 7
- Avg Tokens / Second
- 13.85
- Avg Time to First Token (ms)
- 19021.00
- Last Updated
- Sep 1, 2026
All chutes models
7 tracked · fastest first| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| Gemma 4 31B | 9.64 | 7.43 | 11.80 | 3030.00 |
| Kimi K2.6 | 3.34 | 2.09 | 4.30 | 19500.00 |
| Kimi K2.6 | 2.67 | 0.94 | 5.10 | 26900.00 |
| Qwen3.8 27B | 2.49 | 1.17 | 4.65 | 33700.00 |
| Qwen3.8 27B | 1.37 | 1.37 | 1.37 | 41200.00 |
| GLM 5.1 | 0.97 | 0.97 | 0.97 | 65000.00 |
| GLM 5.1 | 0.95 | 0.72 | 1.21 | 67600.00 |
Frequently Asked Questions
Which chutes model is fastest?
Based on recent tests, Gemma 4 31B shows the highest average throughput among tracked chutes models.
How many recent measurements feed this dashboard?
This provider summary aggregates 2493 individual prompts measured across 2415 monitoring runs over the past month.