llm-benchmarks
githubdrose.io

friendli Provider Benchmarks


Measured over the last 30 days

Models Tracked
7
Avg Tokens / Second
19.65
Avg Time to First Token (ms)
9500.70
Last Updated
Sep 1, 2026

All friendli models

7 tracked · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Gemma 4 31B70.7022.00132.00420.00
GLM 5.245.901.5593.703310.00
GLM 5.244.807.4467.503230.00
Gemma 4 31B28.905.2447.003140.00
DeepSeek V3.220.309.8837.002010.00
MiniMax M2.57.204.0912.009330.00
GLM 5.16.985.707.918820.00

Frequently Asked Questions

Which friendli model is fastest?
Based on recent tests, Gemma 4 31B shows the highest average throughput among tracked friendli models.
How many recent measurements feed this dashboard?
This provider summary aggregates 2752 individual prompts measured across 2627 monitoring runs over the past month.