Measured over the last 30 days
- Models Tracked
- 11
- Avg Tokens / Second
- 21.81
- Avg Time to First Token (ms)
- 4347.27
- Last Updated
- Oct 14, 2026
All nextbit models
11 live · one row per model · fastest first| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| UnslopNemo 12B | 63.90 | 63.90 | 63.90 | 490.00 |
| Gemma 2 27B | 45.00 | 44.70 | 45.30 | 570.00 |
| Gemma 4 26B A4B | 36.00 | 11.10 | 53.10 | 780.00 |
| ReMM SLERP 13B | 22.10 | 22.10 | 22.10 | 500.00 |
| Gemma 3 27B | 18.60 | 18.60 | 18.60 | 1200.00 |
| Llama 3.3 Euryale 70B | 13.40 | 3.78 | 22.10 | 2820.00 |
| Qwen3 14B | 11.30 | 9.39 | 13.20 | 5080.00 |
| DeepSeek V4 Flash 0731 | 9.37 | 9.37 | 9.37 | 6350.00 |
| DeepSeek V4 Pro 0423 | 7.91 | 6.77 | 8.50 | 7290.00 |
| DeepSeek V4 Flash 0423 | 7.81 | 5.29 | 10.20 | 7940.00 |
| DeepSeek V4.1 Flash | 4.55 | 3.53 | 6.75 | 14800.00 |
Frequently Asked Questions
Which nextbit model is fastest?
Based on recent tests, UnslopNemo 12B shows the highest average throughput among tracked nextbit models.
How many recent measurements feed this dashboard?
This provider summary aggregates 951 individual prompts measured across 920 monitoring runs over the past month.