Measured over the last 30 days
- Models Tracked
- 7
- Avg Tokens / Second
- 24.14
- Avg Time to First Token (ms)
- 4533.09
- Last Updated
- Sep 1, 2026
All sambanova models
7 tracked · fastest first| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| gpt-oss-120b | 54.70 | 13.30 | 83.00 | 2490.00 |
| DeepSeek V3.1 | 49.70 | 45.60 | 56.20 | 980.00 |
| MiniMax M3 | 39.70 | 39.70 | 39.70 | 1570.00 |
| Gemma 4 31B | 39.20 | 36.50 | 41.40 | 1550.00 |
| MiniMax M2.7 | 31.20 | 23.40 | 42.50 | 2350.00 |
| DeepSeek V3.2 | 26.10 | 9.43 | 40.10 | 3570.00 |
| MiniMax M2.7 | 24.40 | 22.60 | 28.00 | 3010.00 |
Frequently Asked Questions
Which sambanova model is fastest?
Based on recent tests, gpt-oss-120b shows the highest average throughput among tracked sambanova models.
How many recent measurements feed this dashboard?
This provider summary aggregates 814 individual prompts measured across 726 monitoring runs over the past month.