Measured on novita
5 runs- Avg Tokens / Second
- 27.65
- Avg Time to First Token (ms)
- 970.00
- Runs Analysed
- 5
- Last Updated
- Sep 1, 2026, 04:05 AM
Throughput distribution
Throughput over time
Generated throughput, including reasoning tokens — so a thinking model's line does not collapse; the table ranks on visible tokens · one cell per model, showing its best-covered provider · shared vertical scale, 0 to 25 tok/s (99th percentile) · dashed rule is the model's own mean · 1 further provider not drawn · 1 samples above the ceiling drawn at it
Every provider serving this model
2 measured| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| novita | Kimi K2 0711 | 23.60 | 22.50 | 25.80 | 1220.00 |
| novita | Kimi K2 0711 | 31.70 | 31.70 | 31.70 | 720.00 |
Frequently Asked Questions
How fast is Kimi K2 0711?
The latest rolling average throughput is 27.65 tokens per second with an average time to first token of 970.00 ms across 5 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 1, 2026, 04:05 AM.