llm-benchmarks
githubdrose.io

scaledown Provider Benchmarks


Measured over the last 30 days

Models Tracked
1
Avg Tokens / Second
28.60
Avg Time to First Token (ms)
730.00
Last Updated
Oct 13, 2026

All scaledown models

1 live · one row per model · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Summarize28.6028.6028.60730.00

Frequently Asked Questions

Which scaledown model is fastest?
Based on recent tests, Summarize shows the highest average throughput among tracked scaledown models.
How many recent measurements feed this dashboard?
This provider summary aggregates 1 individual prompts measured across 1 monitoring runs over the past month.