llm-benchmarks
githubdrose.io

crusoe Provider Benchmarks


Measured over the last 30 days

Models Tracked
11
Avg Tokens / Second
21.29
Avg Time to First Token (ms)
10427.33
Last Updated
Sep 1, 2026

All crusoe models

11 tracked · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Nemotron 3 Nano 30B A3B89.1086.2092.10550.00
Nemotron 3 Nano 30B A3B72.1049.2088.30750.00
Llama 3.3 70B Instruct45.4024.4058.40840.00
Gemma 4 31B35.9025.3054.40560.00
GLM 5.234.1019.9045.601410.00
DeepSeek V3 032430.208.6346.001280.00
GLM 5.229.608.1743.402650.00
DeepSeek V3 032429.3014.0037.101110.00
Llama 3.3 70B Instruct21.4019.9022.801510.00
Kimi K2.68.251.1518.1022600.00
GLM 5.15.024.755.3812400.00

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 2981 individual prompts measured across 2820 monitoring runs over the past month.