Benchmark Overview
58.20
190.00
239
Apr 3, 2026, 09:04 AM
Key Insights
mixtral-8x7b streams at 58.20 tokens/second on average across the last 239 benchmark runs.
Performance fluctuated by 105.22 tokens/second (180.8% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 190.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Apr 3, 2026, 09:04 AM based on 239 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.
mixtral-8x7b
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| together | mixtral-8x7b | 58.20 | 8.78 | 114.00 | 190.00 |
Frequently Asked Questions
The latest rolling average throughput is 58.20 tokens per second with an average time to first token of 190.00 ms across 239 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Apr 3, 2026, 09:04 AM.