Benchmark Overview
34.80
870.00
185
Mar 8, 2026, 06:05 AM
Key Insights
llama-3.2-90b streams at 34.80 tokens/second on average across the last 185 benchmark runs.
Performance fluctuated by 71.39 tokens/second (205.1% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 870.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on Mar 8, 2026, 06:05 AM based on 185 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) |
|---|---|---|---|---|---|
| deepinfra | llama-3.2-90b | 34.80 | 3.71 | 75.10 | 870.00 |
Frequently Asked Questions
The latest rolling average throughput is 34.80 tokens per second with an average time to first token of 870.00 ms across 185 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 8, 2026, 06:05 AM.