Measured over the last 30 days
- Models Tracked
- 5
- Avg Tokens / Second
- 30.60
- Avg Time to First Token (ms)
- 3938.00
- Last Updated
- Oct 16, 2026
All friendli models
5 live · one row per model · fastest first · 2 folded behind their current lane| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| GLM 5.2 | 56.10 | 48.00 | 61.80 | 730.00 |
| Gemma 4 31B | 46.50 | 4.62 | 89.40 | 1290.00 |
| DeepSeek V3.2 | 28.60 | 5.31 | 61.70 | 1760.00 |
| MiniMax M2.5 | 15.40 | 2.90 | 31.90 | 5610.00 |
| GLM 5.1 | 6.40 | 2.98 | 7.93 | 10300.00 |
Frequently Asked Questions
Which friendli model is fastest?
Based on recent tests, GLM 5.2 shows the highest average throughput among tracked friendli models.
How many recent measurements feed this dashboard?
This provider summary aggregates 817 individual prompts measured across 791 monitoring runs over the past month.