Benchmark Overview
101.00
0.24
86
Oct 28, 2025, 01:18 PM
Key Insights
llama-3.3-70b streams at 101.00 tokens/second on average across the last 86 benchmark runs.
Performance fluctuated by 105.80 tokens/second (104.8% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 0.24 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Oct 28, 2025, 01:18 PM based on 86 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 | 101.00 | 22.20 | 128.00 | 0.24 |
Frequently Asked Questions
The latest rolling average throughput is 101.00 tokens per second with an average time to first token of 0.24 ms across 86 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 28, 2025, 01:18 PM.