Measured over the last 30 days
- Models Tracked
- 15
- Avg Tokens / Second
- 18.36
- Avg Time to First Token (ms)
- 9981.75
- Last Updated
- Sep 1, 2026
All akashml models
15 tracked · fastest first| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| Llama 3.3 70B Instruct | 29.00 | 19.00 | 38.70 | 960.00 |
| gpt-oss-120b | 25.60 | 25.60 | 25.60 | 1060.00 |
| GLM 5.2 | 25.40 | 25.30 | 25.40 | 1620.00 |
| Llama 3.3 70B Instruct | 24.20 | 8.16 | 34.40 | 1660.00 |
| Llama 3.3 70B Instruct | 21.00 | 6.93 | 34.60 | 1840.00 |
| gpt-oss-120b | 16.10 | 6.83 | 26.70 | 4100.00 |
| gpt-oss-120b | 15.20 | 15.20 | 15.20 | 3200.00 |
| Qwen3.8 27B | 12.10 | 12.10 | 12.10 | 4520.00 |
| Qwen3.5-35B-A3B | 11.90 | 8.87 | 14.50 | 5490.00 |
| Qwen3.5-35B-A3B | 11.70 | 8.81 | 15.30 | 5560.00 |
| Qwen3.8 27B | 10.30 | 1.16 | 14.90 | 19800.00 |
| Llama 3.3 70B Instruct | 8.90 | 8.90 | 8.90 | 5830.00 |
| Qwen3.6 35B A3B | 7.65 | 6.52 | 10.10 | 8350.00 |
| Qwen3.6 35B A3B | 3.97 | 3.97 | 3.97 | 16200.00 |
| DeepSeek V4 Flash 0731 | 1.45 | 0.68 | 2.45 | 52900.00 |
Frequently Asked Questions
Which akashml model is fastest?
Based on recent tests, Llama 3.3 70B Instruct shows the highest average throughput among tracked akashml models.
How many recent measurements feed this dashboard?
This provider summary aggregates 2231 individual prompts measured across 2083 monitoring runs over the past month.