Measured over the last 30 days
- Models Tracked
- 22
- Avg Tokens / Second
- 45.70
- Avg Time to First Token (ms)
- 0.00
- Last Updated
- Aug 14, 2026
| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| GPT-oss-120b | 98.70 | 5.87 | 213.00 | 0.00 |
| Nemotron-Lightning-3.5-30B-A3B | 82.20 | 2.21 | 251.00 | 0.00 |
| GPT-oss-20b | 74.40 | 14.60 | 158.00 | 0.00 |
| qwen3-reranker-8b | 62.20 | 2.30 | 121.00 | 0.00 |
| MiniMax-M2.7 | 61.30 | 4.29 | 193.00 | 0.00 |
| nemotron-3-ultra-550b-a55b | 59.50 | 9.21 | 148.00 | 0.00 |
| kimi-k2p7-code-fast | 55.90 | 34.90 | 85.40 | 0.00 |
| MiniMax-M3 | 53.90 | 6.13 | 113.00 | 0.00 |
| glm-5p2-fast | 52.80 | 1.23 | 159.00 | 0.00 |
| qwen3p7-plus | 52.70 | 6.46 | 248.00 | 0.00 |
| kimi-k2p6-turbo | 49.40 | 3.97 | 94.70 | 0.00 |
| Kimi-K2.7-Code | 36.30 | 1.05 | 72.50 | 0.00 |
| Kimi-K2.6 | 35.60 | 3.21 | 66.20 | 0.00 |
| DeepSeek-V4-Flash | 31.80 | 1.67 | 61.10 | 0.00 |
| GLM-5.2 | 31.20 | 3.52 | 91.90 | 0.00 |
| DeepSeek-V4-Pro | 30.40 | 1.15 | 49.70 | 0.00 |
| kimi-k3-fast | 30.40 | 1.17 | 59.60 | 0.00 |
| glm-5p1 | 29.50 | 8.10 | 63.10 | 0.00 |
| Kimi-K3 | 29.10 | 1.74 | 57.80 | 0.00 |
| DeepSeek-V4-Flash-0731 | 28.60 | 1.10 | 73.10 | 0.00 |
| accounts/fireworks/models/muse-glimmer-30b | 15.20 | 1.91 | 27.40 | 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 5664 individual prompts measured across 4937 monitoring runs over the past month.