Measured over the last 30 days
- Models Tracked
- 2
- Avg Tokens / Second
- 112.35
- Avg Time to First Token (ms)
- 620.00
- Last Updated
- Sep 25, 2026
| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| Gemma 4 31B | 127.00 | 71.40 | 158.00 | 470.00 |
| gpt-oss-120b | 97.70 | 16.70 | 138.00 | 770.00 |
Frequently Asked Questions
Which cerebras model is fastest?
Based on recent tests, Gemma 4 31B shows the highest average throughput among tracked cerebras models.
How many recent measurements feed this dashboard?
This provider summary aggregates 484 individual prompts measured across 473 monitoring runs over the past month.