llm-benchmarks
githubdrose.io

crusoe Provider Benchmarks


Measured over the last 30 days

Models Tracked
6
Avg Tokens / Second
26.42
Avg Time to First Token (ms)
4821.67
Last Updated
Oct 14, 2026

All crusoe models

6 live · one row per model · fastest first · 2 folded behind their current lane
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Nemotron 3 Nano 30B A3B53.5053.5053.50900.00
gpt-oss-120b38.2038.2038.201200.00
Llama 3.3 70B Instruct28.0013.5042.502280.00
Gemma 4 31B23.409.5963.70840.00
DeepSeek V4.1 Flash12.0012.0012.005210.00
Kimi K2.63.442.574.3218500.00

Frequently Asked Questions

Which crusoe model is fastest?
Based on recent tests, Nemotron 3 Nano 30B A3B shows the highest average throughput among tracked crusoe models.
How many recent measurements feed this dashboard?
This provider summary aggregates 1489 individual prompts measured across 1358 monitoring runs over the past month.