Measured over the last 30 days
- Models Tracked
- 14
- Avg Tokens / Second
- 40.49
- Avg Time to First Token (ms)
- 6114.29
- Last Updated
- Nov 18, 2026
All primeintellect models
14 live · one row per model · fastest first · 7 folded behind their current lane| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| Moondream 3 Preview | 86.50 | 6.48 | 120.00 | 810.00 |
| Moondream 3.1 | 82.50 | 23.90 | 120.00 | 700.00 |
| gpt-oss-20b | 80.00 | 53.20 | 118.00 | 680.00 |
| DeepSeek V4 Flash 0731 | 60.40 | 43.90 | 74.60 | 1000.00 |
| gpt-oss-120b | 52.50 | 49.30 | 55.70 | 970.00 |
| Gemma 4 26B A4B | 48.40 | 25.10 | 81.70 | 690.00 |
| Ripple 65B Preview | 33.10 | 30.20 | 36.00 | 800.00 |
| Nemotron 3.5 Super VL | 31.50 | 9.73 | 75.50 | 2890.00 |
| Gemma 4 31B | 30.10 | 5.61 | 52.70 | 590.00 |
| Qwen3.6 35B A3B | 22.80 | 4.37 | 58.70 | 8560.00 |
| Qwen3.5-9B | 17.30 | 17.30 | 17.30 | 2840.00 |
| DeepSeek V4.1 Flash 1017 | 15.40 | 5.53 | 37.20 | 5370.00 |
| deepseek-v4.1-flash | 3.97 | 3.97 | 3.97 | 15800.00 |
| Qwen3.8 27B | 2.43 | 0.77 | 8.21 | 43900.00 |
Frequently Asked Questions
Which primeintellect model is fastest?
Based on recent tests, Moondream 3 Preview shows the highest average throughput among tracked primeintellect models.
How many recent measurements feed this dashboard?
This provider summary aggregates 2149 individual prompts measured across 1850 monitoring runs over the past month.