← All models

gemma4:31b

32.7B parameters BF16 262,144 token context completionthinkingtoolsvision
145.7
output tokens / second
123 tokens · 0.84s server · 1.19s request

Performance statistics

Calculated live from valid twenty-minute RRDtool samples.

Range Latest Average Lowest Median P50 P05 Highest Std dev Variability CV Trend Data coverage
Last 24 hours 145.0 115.0 30.2 119.8 54.5 175.8 36.3 31.6% -0.4% 72 samples 100.0%
Last 7 days 145.0 117.4 19.2 124.3 50.2 189.6 39.3 33.5% +10.6% 504 samples 100.0%
Last 30 days 145.0 113.6 4.1 117.6 47.3 195.2 40.5 35.6% +7.4% 2160 samples 100.0%

P05: 5% of twenty-minute throughput samples are at or below this value; it represents lower-tail performance. CV: standard deviation ÷ average; lower is more stable. Trend: second-half average versus first-half average. Data coverage: valid samples versus all expected twenty-minute slots in the selected range.

Last 24 hours

gemma4:31b throughput for Last 24 hours