Measured over the last 30 days
- Models Tracked
- 20
- Avg Tokens / Second
- 17.31
- Avg Time to First Token (ms)
- 9893.60
- Last Updated
- Sep 1, 2026
All cloudflare models
20 tracked · fastest first| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| Llama 3.2 3B Instruct | 82.90 | 70.40 | 96.70 | 520.00 |
| Llama 3.2 1B Instruct | 51.70 | 29.90 | 62.90 | 680.00 |
| Llama 3.2 1B Instruct | 51.10 | 22.60 | 135.00 | 1050.00 |
| Gemma 4 26B A4B | 48.20 | 36.50 | 70.50 | 700.00 |
| Gemma 4 26B A4B | 43.20 | 33.60 | 51.40 | 750.00 |
| DeepSeek V4 Flash 0423 | 36.80 | 29.50 | 49.40 | 850.00 |
| Mistral Small 3.1 24B | 29.10 | 12.20 | 47.40 | 1080.00 |
| Llama 3.3 70B Instruct | 29.00 | 27.00 | 31.00 | 880.00 |
| Granite 4.0 Micro | 28.40 | 25.30 | 30.40 | 610.00 |
| GLM 5.2 | 28.00 | 16.70 | 46.90 | 1980.00 |
| Granite 4.0 Micro | 25.60 | 21.00 | 33.30 | 910.00 |
| Mistral Small 3.1 24B | 25.50 | 21.90 | 28.40 | 860.00 |
| Qwen2.5 Coder 32B Instruct | 25.30 | 23.80 | 26.30 | 610.00 |
| Qwen2.5 Coder 32B Instruct | 24.10 | 16.70 | 27.10 | 810.00 |
| DeepSeek V4 Flash 0731 | 22.40 | 15.10 | 26.10 | 2400.00 |
| Llama 3.1 8B Instruct | 16.20 | 14.90 | 16.80 | 840.00 |
| Kimi K2.7 Code | 9.78 | 7.10 | 13.00 | 5810.00 |
| Kimi K2.6 | 4.86 | 3.77 | 6.01 | 12600.00 |
| GLM 4.7 Flash | 3.64 | 3.64 | 3.64 | 16100.00 |
| GLM 4.7 Flash | 2.69 | 2.01 | 3.35 | 23300.00 |
Frequently Asked Questions
Which cloudflare model is fastest?
Based on recent tests, Llama 3.2 3B Instruct shows the highest average throughput among tracked cloudflare models.
How many recent measurements feed this dashboard?
This provider summary aggregates 1468 individual prompts measured across 1214 monitoring runs over the past month.