llm-benchmarks
githubdrose.io

darkbloom Provider Benchmarks


Measured over the last 30 days

Models Tracked
7
Avg Tokens / Second
13.60
Avg Time to First Token (ms)
10978.55
Last Updated
Sep 1, 2026

All darkbloom models

7 tracked · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Gemma 4 26B A4B39.2010.6057.102410.00
Qwen3.5-35B-A3B6.836.836.838740.00
gpt-oss-20b6.715.747.678810.00
Qwen3.5-35B-A3B6.416.416.419500.00
Qwen3.6 35B A3B4.754.754.7512900.00
Free Models Router3.921.505.2614500.00
Qwen3.6 35B A3B2.012.012.0131900.00

Frequently Asked Questions

Which darkbloom model is fastest?
Based on recent tests, Gemma 4 26B A4B shows the highest average throughput among tracked darkbloom models.
How many recent measurements feed this dashboard?
This provider summary aggregates 931 individual prompts measured across 906 monitoring runs over the past month.