llm-benchmarks
githubdrose.io

fireworks Provider Benchmarks


Measured over the last 30 days

Models Tracked
22
Avg Tokens / Second
45.70
Avg Time to First Token (ms)
0.00
Last Updated
Aug 14, 2026

All fireworks models

22 tracked · fastest first
fireworks site
ModelAvg Toks/SecMinMaxAvg TTF (ms)
GPT-oss-120b98.705.87213.000.00
Nemotron-Lightning-3.5-30B-A3B82.202.21251.000.00
GPT-oss-20b74.4014.60158.000.00
qwen3-reranker-8b62.202.30121.000.00
MiniMax-M2.761.304.29193.000.00
nemotron-3-ultra-550b-a55b59.509.21148.000.00
kimi-k2p7-code-fast55.9034.9085.400.00
MiniMax-M353.906.13113.000.00
glm-5p2-fast52.801.23159.000.00
qwen3p7-plus52.706.46248.000.00
kimi-k2p6-turbo49.403.9794.700.00
Kimi-K2.7-Code36.301.0572.500.00
Kimi-K2.635.603.2166.200.00
DeepSeek-V4-Flash31.801.6761.100.00
GLM-5.231.203.5291.900.00
DeepSeek-V4-Pro30.401.1549.700.00
kimi-k3-fast30.401.1759.600.00
glm-5p129.508.1063.100.00
Kimi-K329.101.7457.800.00
DeepSeek-V4-Flash-073128.601.1073.100.00
accounts/fireworks/models/muse-glimmer-30b15.201.9127.400.00
Inkling4.304.304.300.00

Frequently Asked Questions

Which fireworks model is fastest?
Based on recent tests, GPT-oss-120b shows the highest average throughput among tracked fireworks models.
How many recent measurements feed this dashboard?
This provider summary aggregates 5664 individual prompts measured across 4937 monitoring runs over the past month.