Benchmark Overview
46.90
350.00
1282
Jul 16, 2026, 03:40 PM
Key Insights
llama-3.2-90b streams at 46.90 tokens/second on average across the last 1282 benchmark runs.
Performance fluctuated by 36.80 tokens/second (78.5% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 350.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Jul 16, 2026, 03:40 PM based on 1282 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 | 46.90 | 13.10 | 49.90 | 350.00 |
Frequently Asked Questions
The latest rolling average throughput is 46.90 tokens per second with an average time to first token of 350.00 ms across 1282 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jul 16, 2026, 03:40 PM.