Measured over the last 30 days
- Models Tracked
- 26
- Avg Tokens / Second
- 13.73
- Avg Time to First Token (ms)
- 12909.45
- Last Updated
- Sep 1, 2026
All digitalocean models
26 tracked · fastest first| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| Qwen3 Coder 30B A3B Instruct | 73.90 | 73.90 | 73.90 | 550.00 |
| DeepSeek V4 Pro 0423 | 34.80 | 28.40 | 42.90 | 650.00 |
| DeepSeek V3.2 | 27.40 | 6.77 | 45.10 | 2340.00 |
| DeepSeek V4 Pro 0423 | 17.80 | 2.67 | 44.90 | 1780.00 |
| Qwen3.8 2.4T A95B | 17.80 | 9.79 | 28.50 | 3470.00 |
| MiMo-V2.5-Pro | 14.00 | 5.17 | 17.20 | 4300.00 |
| GLM 5.2 | 13.90 | 0.60 | 33.00 | 17000.00 |
| Qwen3.8 2.4T A95B | 13.80 | 10.70 | 17.70 | 4090.00 |
| GLM 5.2 | 11.30 | 2.29 | 22.30 | 10100.00 |
| gpt-oss-120b | 11.10 | 7.34 | 17.30 | 5210.00 |
| Llama 4 Maverick | 9.85 | 6.31 | 39.30 | 1160.00 |
| Llama 4 Maverick | 9.77 | 3.74 | 20.80 | 1210.00 |
| DeepSeek V4 Flash 0423 | 6.89 | 2.23 | 12.90 | 1370.00 |
| DeepSeek V4 Flash 0423 | 6.12 | 2.24 | 9.64 | 2230.00 |
| MiniMax M2.5 | 5.45 | 1.81 | 10.30 | 16100.00 |
| Kimi K2.6 | 3.62 | 2.47 | 4.91 | 17900.00 |
| Kimi K2.5 | 2.47 | 1.12 | 5.63 | 31400.00 |
| DeepSeek V4 Flash 0731 | 2.36 | 0.92 | 7.94 | 32400.00 |
| DeepSeek V4 Pro 0813 | 2.31 | 2.31 | 2.31 | 25800.00 |
| DeepSeek V4 Flash 0731 | 2.27 | 1.70 | 2.70 | 28100.00 |
| Nemotron 3 Super | 1.87 | 1.14 | 2.58 | 30900.00 |
| Kimi K2.6 | 1.28 | 0.91 | 1.64 | 51500.00 |
| Kimi K2.5 | 1.21 | 1.21 | 1.21 | 49600.00 |
| Qwen3.5 397B A17B | 0.72 | 0.55 | 1.13 | 88000.00 |
| GLM 5.1 | 0.68 | 0.65 | 0.71 | 88200.00 |
| Qwen3.5 397B A17B | 0.66 | 0.63 | 0.68 | 91700.00 |
Frequently Asked Questions
Which digitalocean model is fastest?
Based on recent tests, Qwen3 Coder 30B A3B Instruct shows the highest average throughput among tracked digitalocean models.
How many recent measurements feed this dashboard?
This provider summary aggregates 4754 individual prompts measured across 4002 monitoring runs over the past month.