Measured over the last 30 days
- Models Tracked
- 7
- Avg Tokens / Second
- 19.65
- Avg Time to First Token (ms)
- 9500.70
- Last Updated
- Sep 1, 2026
All friendli models
7 tracked · fastest first| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| Gemma 4 31B | 70.70 | 22.00 | 132.00 | 420.00 |
| GLM 5.2 | 45.90 | 1.55 | 93.70 | 3310.00 |
| GLM 5.2 | 44.80 | 7.44 | 67.50 | 3230.00 |
| Gemma 4 31B | 28.90 | 5.24 | 47.00 | 3140.00 |
| DeepSeek V3.2 | 20.30 | 9.88 | 37.00 | 2010.00 |
| MiniMax M2.5 | 7.20 | 4.09 | 12.00 | 9330.00 |
| GLM 5.1 | 6.98 | 5.70 | 7.91 | 8820.00 |
Frequently Asked Questions
Which friendli model is fastest?
Based on recent tests, Gemma 4 31B shows the highest average throughput among tracked friendli models.
How many recent measurements feed this dashboard?
This provider summary aggregates 2752 individual prompts measured across 2627 monitoring runs over the past month.