Benchmark Overview
79.50
500.00
1400
Jun 25, 2026, 02:42 AM
Key Insights
llama-3.3-70b streams at 79.50 tokens/second on average across the last 1400 benchmark runs.
Performance fluctuated by 116.97 tokens/second (147.1% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 500.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on Jun 25, 2026, 02:42 AM based on 1400 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) |
|---|---|---|---|---|---|
| bedrock | llama-3.3-70b | 79.50 | 1.03 | 118.00 | 500.00 |
Frequently Asked Questions
The latest rolling average throughput is 79.50 tokens per second with an average time to first token of 500.00 ms across 1400 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 25, 2026, 02:42 AM.