Benchmark Overview
32.60
0.00
154
Jun 11, 2026, 03:16 PM
Key Insights
llama-3.3-70b streams at 32.60 tokens/second on average across the last 154 benchmark runs.
Performance fluctuated by 66.15 tokens/second (202.9% coefficient of variation), indicating variable behavior across benchmark runs.
Latest measurements completed on Jun 11, 2026, 03:16 PM based on 154 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-3.3-70b
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| together | llama-3.3-70b | 32.60 | 1.25 | 67.40 | 0.00 |
Frequently Asked Questions
The latest rolling average throughput is 32.60 tokens per second with an average time to first token of 0.00 ms across 154 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 11, 2026, 03:16 PM.