Measured over the last 30 days
- Models Tracked
- 5
- Avg Tokens / Second
- 11.86
- Avg Time to First Token (ms)
- 6296.00
- Last Updated
- Nov 7, 2026
| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| Nemotron 3.5 Lightning | 20.30 | 20.30 | 20.30 | 2970.00 |
| DeepSeek V4.1 Flash 1017 | 13.20 | 7.88 | 22.70 | 4920.00 |
| DeepSeek V4 Flash 0423 | 9.08 | 9.08 | 9.08 | 6360.00 |
| Muse Spark Open | 8.45 | 3.95 | 14.00 | 8420.00 |
| DeepSeek V4.1 Flash | 8.25 | 0.19 | 22.00 | 8810.00 |
Frequently Asked Questions
Which fireworks model is fastest?
Based on recent tests, Nemotron 3.5 Lightning shows the highest average throughput among tracked fireworks models.
How many recent measurements feed this dashboard?
This provider summary aggregates 1386 individual prompts measured across 1286 monitoring runs over the past month.