Benchmark Overview
24.70
1470.00
240
Apr 3, 2026, 12:02 PM
Key Insights
llama-3.2-11b streams at 24.70 tokens/second on average across the last 240 benchmark runs.
Performance fluctuated by 78.69 tokens/second (318.6% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1470.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Apr 3, 2026, 12:02 PM based on 240 total samples.
Performance Distribution
Distribution of throughput measurements showing performance consistency across benchmark runs.
Performance Over Time
Historical performance trends showing how throughput has changed over the benchmarking period.
llama-3.2-11b
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| deepinfra | llama-3.2-11b | 24.70 | 1.81 | 80.50 | 1470.00 |
Frequently Asked Questions
The latest rolling average throughput is 24.70 tokens per second with an average time to first token of 1470.00 ms across 240 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Apr 3, 2026, 12:02 PM.