llm-benchmarks
githubdrose.io

featherless Provider Benchmarks


Measured over the last 30 days

Models Tracked
1
Avg Tokens / Second
1.71
Avg Time to First Token (ms)
36000.00
Last Updated
Oct 29, 2026

All featherless models

1 live · one row per model · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Step 5 Preview1.711.711.7136000.00

Frequently Asked Questions

Which featherless model is fastest?
Based on recent tests, Step 5 Preview shows the highest average throughput among tracked featherless models.
How many recent measurements feed this dashboard?
This provider summary aggregates 54 individual prompts measured across 54 monitoring runs over the past month.