llm-benchmarks
githubdrose.io

fireworks Provider Benchmarks


Measured over the last 30 days

Models Tracked
4
Avg Tokens / Second
16.95
Avg Time to First Token (ms)
8797.50
Last Updated
Sep 23, 2026

All fireworks models

4 live · one row per model · fastest first · 1 folded behind their current lane
fireworks site
ModelAvg Toks/SecMinMaxAvg TTF (ms)
GLM 5.245.0016.8060.101130.00
DeepSeek V4 Flash 073111.803.6521.907290.00
Muse Glimmer 30B7.807.348.267370.00
DeepSeek V4.1 Flash3.193.193.1919400.00

Frequently Asked Questions

Which fireworks model is fastest?
Based on recent tests, GLM 5.2 shows the highest average throughput among tracked fireworks models.
How many recent measurements feed this dashboard?
This provider summary aggregates 742 individual prompts measured across 714 monitoring runs over the past month.