llm-benchmarks
githubdrose.io

ionet Provider Benchmarks


Measured over the last 30 days

Models Tracked
7
Avg Tokens / Second
27.04
Avg Time to First Token (ms)
2925.71
Last Updated
Oct 17, 2026

All ionet models

7 live · one row per model · fastest first · 1 folded behind their current lane
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Gemma 4 26B A4B46.706.7560.90950.00
Mistral Nemo41.0041.0041.00640.00
Gemma 4 31B31.7029.5033.80660.00
DeepSeek V4 Pro 081330.2028.3033.101300.00
MiMo-V2.6-Flash20.407.2940.703320.00
Nemotron 3.5 Lightning11.8011.8011.805190.00
Qwen3.6 35B A3B7.467.467.468420.00

Frequently Asked Questions

Which ionet model is fastest?
Based on recent tests, Gemma 4 26B A4B shows the highest average throughput among tracked ionet models.
How many recent measurements feed this dashboard?
This provider summary aggregates 1069 individual prompts measured across 1029 monitoring runs over the past month.