Measured over the last 30 days
- Models Tracked
- 20
- Avg Tokens / Second
- 53.87
- Avg Time to First Token (ms)
- 0.00
- Last Updated
- Aug 9, 2026
| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| LFM2.5-8B-A1B | 109.00 | 17.40 | 141.00 | 0.00 |
| qwen-2-1.5b-instruct | 102.00 | 3.13 | 147.00 | 0.00 |
| Kimi-K2.7-Code | 77.90 | 2.27 | 199.00 | 0.00 |
| qwen-2.5-7b | 70.90 | 40.20 | 92.90 | 0.00 |
| GLM-5.2 | 70.00 | 2.84 | 193.00 | 0.00 |
| Qwen2.5-7B-Instruct-Turbo | 68.10 | 48.30 | 85.00 | 0.00 |
| qwen-3.5-9b | 63.80 | 8.10 | 109.00 | 0.00 |
| Kimi-K2.6 | 61.90 | 2.93 | 138.00 | 0.00 |
| nemotron-3-ultra-550b-a55b | 56.30 | 7.96 | 118.00 | 0.00 |
| GPT-oss-120b | 54.00 | 3.70 | 135.00 | 0.00 |
| gemma-4-31B-it | 53.70 | 2.34 | 104.00 | 0.00 |
| GPT-oss-20b | 50.90 | 4.01 | 167.00 | 0.00 |
| DeepSeek-V4-Flash-0731 | 45.70 | 1.66 | 109.00 | 0.00 |
| llama-3.3-70b | 44.70 | 3.96 | 97.30 | 0.00 |
| Kimi-K3 | 38.40 | 2.78 | 72.70 | 0.00 |
| gemma-3n-e4b-it | 31.90 | 13.00 | 55.00 | 0.00 |
| MiniMax-M3 | 25.90 | 2.87 | 68.70 | 0.00 |
| DeepSeek-V4-Pro | 24.70 | 5.08 | 80.00 | 0.00 |
| Inkling | 24.40 | 10.10 | 47.50 | 0.00 |
| Llama-Guard-4-12B | 3.14 | 0.73 | 4.04 | 0.00 |
Frequently Asked Questions
Which together model is fastest?
Based on recent tests, LFM2.5-8B-A1B shows the highest average throughput among tracked together models.
How many recent measurements feed this dashboard?
This provider summary aggregates 2530 individual prompts measured across 2467 monitoring runs over the past month.