qwen-2.5-72b Benchmarks

Provider: together

Explore real-world latency and throughput results for qwen-2.5-72b. 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 together provider hub to compare every tracked model side-by-side.

Visit together Official Website

Benchmark Overview

Avg Tokens / Second

50.90

Avg Time to First Token (ms)

490.00

Runs Analysed

225

Last Updated

Feb 7, 2026, 12:10 AM

Key Insights

  • qwen-2.5-72b streams at 50.90 tokens/second on average across the last 225 benchmark runs.

  • Performance fluctuated by 67.12 tokens/second (131.9% coefficient of variation), indicating variable behavior across benchmark runs.

  • Average time to first token is 490.00 ms (excellent latency), suitable for latency-sensitive workloads.

  • Latest measurements completed on Feb 7, 2026, 12:10 AM based on 225 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-2.5-72b

Benchmark Samples

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
togetherqwen-2.5-72b50.903.2870.40490.00

Frequently Asked Questions

The latest rolling average throughput is 50.90 tokens per second with an average time to first token of 490.00 ms across 225 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Feb 7, 2026, 12:10 AM.

Related Links