Benchmark Overview
50.40
1730.00
80
Mar 7, 2026, 12:04 AM
Key Insights
llama-3.2-3b streams at 50.40 tokens/second on average across the last 80 benchmark runs.
Performance fluctuated by 115.37 tokens/second (228.9% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1730.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Mar 7, 2026, 12:04 AM based on 80 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-3.2-3b
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| together | llama-3.2-3b | 50.40 | 5.63 | 121.00 | 1730.00 |
Frequently Asked Questions
The latest rolling average throughput is 50.40 tokens per second with an average time to first token of 1730.00 ms across 80 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 7, 2026, 12:04 AM.