llm-benchmarks
githubdrose.io

Gemma 4 26B A4B Benchmarks


Measured on ionet

37 runs
Avg Tokens / Second
45.20
Decode Tokens / Second
—
Avg Time to First Token (ms)
960.00
Runs Analysed
37
Last Updated
Nov 5, 2026, 05:31 PM

Throughput distribution

Throughput over time

Gemma 4 26B A4Bionet44tok/s

Generated throughput, including reasoning tokens — so a thinking model's line does not collapse; the table ranks on visible tokens · one cell per model, showing its best-covered provider · models with at least 4 samples in the window first, fastest of those at the top · shared vertical scale, 0 to 66 tok/s (99th percentile) · dashed rule is the model's own mean

Every lane measuring this model

1 measured · live first · a lane is a provider, a catalogue id and a transport
ProviderLaneAvg Toks/SecMinMaxAvg TTF (ms)n
ionetvia OpenRouter45.206.7562.50960.0037

Frequently Asked Questions

How fast is Gemma 4 26B A4B?
The latest rolling average throughput is 45.20 tokens per second with an average time to first token of 960.00 ms across 37 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Nov 5, 2026, 05:31 PM.

Related models