llm-benchmarks
githubdrose.io

modal Provider Benchmarks


Measured over the last 30 days

Models Tracked
2
Avg Tokens / Second
13.61
Avg Time to First Token (ms)
5575.45
Last Updated
Sep 1, 2026

All modal models

2 tracked · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Qwen3.8 2.4T A95B23.5023.5023.502780.00
Qwen3.8 2.4T A95B22.9014.6032.003420.00

Frequently Asked Questions

Which modal model is fastest?
Based on recent tests, Qwen3.8 2.4T A95B shows the highest average throughput among tracked modal models.
How many recent measurements feed this dashboard?
This provider summary aggregates 31 individual prompts measured across 27 monitoring runs over the past month.