Benchmark Overview
45.90
410.00
1241
May 20, 2026, 01:36 PM
Key Insights
llama-3.2-90b streams at 45.90 tokens/second on average across the last 1241 benchmark runs.
Performance fluctuated by 17.90 tokens/second (39.0% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 410.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 20, 2026, 01:36 PM based on 1241 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-3.2-90b
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| bedrock | llama-3.2-90b | 45.90 | 31.60 | 49.50 | 410.00 |
Frequently Asked Questions
The latest rolling average throughput is 45.90 tokens per second with an average time to first token of 410.00 ms across 1241 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 20, 2026, 01:36 PM.