llm-benchmarks
githubdrose.io

Gemma 4 26B A4B Benchmarks


Measured on parasail

72 runs
Avg Tokens / Second
25.60
Avg Time to First Token (ms)
980.00
Runs Analysed
72
Last Updated
Sep 1, 2026, 03:37 AM

Throughput distribution

Throughput over time

Gemma 4 26B A4Bnextbit1tok/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 · shared vertical scale, 0 to 51 tok/s (99th percentile) · dashed rule is the model's own mean · 10 further providers not drawn

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
parasailGemma 4 26B A4B25.607.0346.00980.00

Frequently Asked Questions

How fast is Gemma 4 26B A4B?
The latest rolling average throughput is 25.60 tokens per second with an average time to first token of 980.00 ms across 72 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 1, 2026, 03:37 AM.

Related models