Benchmark Overview
48.80
1460.00
21
Mar 7, 2026, 12:04 AM
Key Insights
llama-3.2-3b streams at 48.80 tokens/second on average across the last 21 benchmark runs.
Performance fluctuated by 98.50 tokens/second (201.8% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1460.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Mar 7, 2026, 12:04 AM based on 21 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 | 48.80 | 10.50 | 109.00 | 1460.00 |
Frequently Asked Questions
The latest rolling average throughput is 48.80 tokens per second with an average time to first token of 1460.00 ms across 21 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 7, 2026, 12:04 AM.