Measured over the last 30 days
- Models Tracked
- 6
- Avg Tokens / Second
- 33.27
- Avg Time to First Token (ms)
- 2803.33
- Last Updated
- Oct 17, 2026
All sambanova models
6 live · one row per model · fastest first · 1 folded behind their current lane| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| gpt-oss-120b | 78.20 | 68.80 | 86.30 | 900.00 |
| DeepSeek V3.2 | 30.20 | 21.00 | 39.30 | 1960.00 |
| MiniMax M3 | 28.60 | 21.50 | 39.10 | 2210.00 |
| MiniMax M2.7 | 23.40 | 19.40 | 27.40 | 3140.00 |
| Gemma 4 31B | 21.80 | 5.90 | 38.70 | 5300.00 |
| DeepSeek V3.1 | 17.40 | 17.40 | 17.40 | 3310.00 |
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 922 individual prompts measured across 876 monitoring runs over the past month.