llm-benchmarks
githubdrose.io

nearai Provider Benchmarks


Measured over the last 30 days

Models Tracked
1
Avg Tokens / Second
2.72
Avg Time to First Token (ms)
22600.00
Last Updated
Oct 10, 2026

All nearai models

1 live · one row per model · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Qwen3.8 27B2.722.253.4022600.00

Frequently Asked Questions

Which nearai model is fastest?
Based on recent tests, Qwen3.8 27B shows the highest average throughput among tracked nearai models.
How many recent measurements feed this dashboard?
This provider summary aggregates 37 individual prompts measured across 37 monitoring runs over the past month.