Measured over the last 30 days
- Models Tracked
- 4
- Avg Tokens / Second
- 16.95
- Avg Time to First Token (ms)
- 8797.50
- Last Updated
- Sep 23, 2026
All fireworks models
4 live · one row per model · fastest first · 1 folded behind their current lane| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| GLM 5.2 | 45.00 | 16.80 | 60.10 | 1130.00 |
| DeepSeek V4 Flash 0731 | 11.80 | 3.65 | 21.90 | 7290.00 |
| Muse Glimmer 30B | 7.80 | 7.34 | 8.26 | 7370.00 |
| DeepSeek V4.1 Flash | 3.19 | 3.19 | 3.19 | 19400.00 |
Frequently Asked Questions
Which fireworks model is fastest?
Based on recent tests, GLM 5.2 shows the highest average throughput among tracked fireworks models.
How many recent measurements feed this dashboard?
This provider summary aggregates 742 individual prompts measured across 714 monitoring runs over the past month.