qwen-3-32b Benchmarks

Provider: cerebras

Explore real-world latency and throughput results for qwen-3-32b. These measurements come from automated benchmarking runs against the provider APIs using the same harness that powers the public cloud dashboard.

Want a broader view of this vendor? Visit the cerebras provider hub to compare every tracked model side-by-side.

Visit cerebras Official Website

Benchmark Overview

Avg Tokens / Second

223.00

Avg Time to First Token (ms)

0.71

Runs Analysed

586

Last Updated

Oct 19, 2025, 07:04 AM

Key Insights

  • qwen-3-32b streams at 223.00 tokens/second on average across the last 586 benchmark runs.

  • Performance fluctuated by 431.47 tokens/second (193.5% coefficient of variation), indicating variable behavior across benchmark runs.

  • Average time to first token is 0.71 ms (excellent latency), suitable for latency-sensitive workloads.

  • Latest measurements completed on Oct 19, 2025, 07:04 AM based on 586 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.

qwen-3-32b

Benchmark Samples

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
cerebrasqwen-3-32b223.001.53433.000.71

Frequently Asked Questions

The latest rolling average throughput is 223.00 tokens per second with an average time to first token of 0.71 ms across 586 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 19, 2025, 07:04 AM.

Related Links