Measured over the last 30 days
- Models Tracked
- 7
- Avg Tokens / Second
- 12.56
- Avg Time to First Token (ms)
- 13531.43
- Last Updated
- Oct 17, 2026
All darkbloom models
7 live · one row per model · fastest first · 4 folded behind their current lane| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| Gemma 4 26B A4B | 54.60 | 30.90 | 84.80 | 540.00 |
| MiMo-V2.6-Flash | 12.30 | 8.10 | 21.10 | 3580.00 |
| gpt-oss-20b | 6.58 | 5.36 | 7.68 | 9100.00 |
| Nemotron 3.5 Lightning | 4.13 | 4.13 | 4.13 | 14500.00 |
| Qwen3.8 27B | 4.06 | 4.06 | 4.06 | 15100.00 |
| Qwen3.6 35B A3B | 3.86 | 2.29 | 5.86 | 17100.00 |
| Ternary Bonsai 2 27B | 2.41 | 1.07 | 5.85 | 34800.00 |
Frequently Asked Questions
Which darkbloom model is fastest?
Based on recent tests, Gemma 4 26B A4B shows the highest average throughput among tracked darkbloom models.
How many recent measurements feed this dashboard?
This provider summary aggregates 616 individual prompts measured across 607 monitoring runs over the past month.