Measured over the last 30 days
- Models Tracked
- 15
- Avg Tokens / Second
- 27.76
- Avg Time to First Token (ms)
- 5034.00
- Last Updated
- Oct 17, 2026
All coreweave models
15 live · one row per model · fastest first · 6 folded behind their current lane| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| Llama 3.1 8B Instruct | 80.70 | 80.70 | 80.70 | 400.00 |
| Gemma 4 26B A4B | 50.90 | 20.80 | 72.70 | 510.00 |
| GLM 5.2 | 50.40 | 1.07 | 70.00 | 6720.00 |
| Llama 3.3 70B Instruct | 45.10 | 10.50 | 58.50 | 710.00 |
| DeepSeek V3.1 | 42.80 | 41.10 | 44.40 | 680.00 |
| Kimi K2.7 Code | 27.20 | 8.80 | 56.90 | 2640.00 |
| Gemma 4 31B | 24.40 | 3.56 | 47.70 | 1510.00 |
| gpt-oss-20b | 23.90 | 0.92 | 89.20 | 3640.00 |
| DeepSeek V4 Flash 0731 | 16.00 | 1.09 | 38.90 | 7210.00 |
| MiniMax M3 | 13.10 | 2.11 | 32.70 | 6750.00 |
| Nemotron 3.5 Lightning | 12.30 | 12.30 | 12.30 | 4880.00 |
| Kimi K2.6 | 9.37 | 2.33 | 34.10 | 10200.00 |
| gpt-oss-120b | 9.20 | 5.48 | 12.90 | 6560.00 |
| Qwen3.6 35B A3B | 5.81 | 3.90 | 7.17 | 10900.00 |
| DeepSeek V4.1 Flash | 5.16 | 4.72 | 5.61 | 12200.00 |
Frequently Asked Questions
Which coreweave model is fastest?
Based on recent tests, Llama 3.1 8B Instruct shows the highest average throughput among tracked coreweave models.
How many recent measurements feed this dashboard?
This provider summary aggregates 2844 individual prompts measured across 2467 monitoring runs over the past month.