llm-benchmarks
githubdrose.io

liquid Provider Benchmarks


Measured over the last 30 days

Models Tracked
1
Avg Tokens / Second
11.90
Avg Time to First Token (ms)
6780.00
Last Updated
Oct 16, 2026

All liquid models

1 live · one row per model · fastest first · 1 folded behind their current lane
ModelAvg Toks/SecMinMaxAvg TTF (ms)
LFM2.5-24B-A2B11.902.8918.606780.00

Frequently Asked Questions

Which liquid model is fastest?
Based on recent tests, LFM2.5-24B-A2B shows the highest average throughput among tracked liquid models.
How many recent measurements feed this dashboard?
This provider summary aggregates 12 individual prompts measured across 12 monitoring runs over the past month.