Measured on nebius
9 runs- Avg Tokens / Second
- 17.80
- Avg Time to First Token (ms)
- 5290.00
- Runs Analysed
- 9
- Last Updated
- Sep 1, 2026, 04:10 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 1 tok/s (99th percentile) · dashed rule is the model's own mean · 4 further providers 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) |
|---|---|---|---|---|---|
| nebius | Nemotron 3 Super | 21.90 | 20.00 | 24.40 | 2800.00 |
| nebius | Nemotron 3 Super | 13.70 | 4.89 | 22.40 | 7780.00 |
Frequently Asked Questions
How fast is Nemotron 3 Super?
The latest rolling average throughput is 17.80 tokens per second with an average time to first token of 5290.00 ms across 9 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, 04:10 AM.