llm-benchmarks
githubdrose.io

dekallm Provider Benchmarks


Measured over the last 30 days

Models Tracked
5
Avg Tokens / Second
23.68
Avg Time to First Token (ms)
8228.00
Last Updated
Sep 12, 2026

All dekallm models

5 live · one row per model · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Qwen3 30B A3B Instruct 250756.4056.4056.40620.00
Gemma 4 26B A4B43.3043.3043.30840.00
Qwen3.6 35B A3B9.099.099.097010.00
gpt-oss-120b7.347.347.346970.00
gpt-oss-20b2.292.292.2925700.00

Frequently Asked Questions

Which dekallm model is fastest?
Based on recent tests, Qwen3 30B A3B Instruct 2507 shows the highest average throughput among tracked dekallm models.
How many recent measurements feed this dashboard?
This provider summary aggregates 1292 individual prompts measured across 1243 monitoring runs over the past month.