Measured over the last 30 days
- Models Tracked
- 20
- Avg Tokens / Second
- 45.81
- Avg Time to First Token (ms)
- 0.00
- Last Updated
- Aug 8, 2026
| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| GPT-oss-120b | 98.40 | 5.87 | 211.00 | 0.00 |
| GPT-oss-20b | 74.40 | 14.60 | 158.00 | 0.00 |
| MiniMax-M2.7 | 64.60 | 8.23 | 136.00 | 0.00 |
| qwen3-reranker-8b | 63.50 | 11.10 | 86.30 | 0.00 |
| MiniMax-M3 | 59.10 | 9.40 | 113.00 | 0.00 |
| nemotron-3-ultra-550b-a55b | 59.10 | 9.21 | 84.70 | 0.00 |
| kimi-k2p7-code-fast | 55.90 | 34.90 | 85.40 | 0.00 |
| qwen3p7-plus | 50.50 | 12.00 | 77.10 | 0.00 |
| kimi-k2p6-turbo | 50.10 | 13.30 | 94.70 | 0.00 |
| glm-5p2-fast | 49.00 | 1.23 | 101.00 | 0.00 |
| Kimi-K2.6 | 38.30 | 1.77 | 79.80 | 0.00 |
| DeepSeek-V4-Flash | 34.00 | 5.03 | 61.10 | 0.00 |
| Kimi-K2.7-Code | 33.10 | 1.56 | 65.30 | 0.00 |
| GLM-5.2 | 32.30 | 3.52 | 109.00 | 0.00 |
| DeepSeek-V4-Pro | 31.10 | 2.15 | 49.70 | 0.00 |
| kimi-k3-fast | 30.90 | 1.17 | 49.20 | 0.00 |
| Kimi-K3 | 30.50 | 1.74 | 57.00 | 0.00 |
| DeepSeek-V4-Flash-0731 | 29.00 | 1.10 | 73.10 | 0.00 |
| glm-5p1 | 28.10 | 2.47 | 63.10 | 0.00 |
| Inkling | 4.30 | 4.30 | 4.30 | 0.00 |
Frequently Asked Questions
Which fireworks model is fastest?
Based on recent tests, GPT-oss-120b shows the highest average throughput among tracked fireworks models.
How many recent measurements feed this dashboard?
This provider summary aggregates 4327 individual prompts measured across 3811 monitoring runs over the past month.