Qwen 2.5 Coder 32B by deepinfra Benchmarks

No Successful Benchmarks

This model has never returned successful benchmark results. It may be misconfigured or unavailable.

Last benchmark: February 16, 2026

Benchmark Overview

Avg Tokens / Second

30.30

Avg Time to First Token (ms)

3880.00

Runs Analysed

236

Last Updated

Feb 16, 2026, 09:00 AM

Qwen 2.5 Coder 32B streams at 30.30 tokens/second on average across the last 236 benchmark runs.
Performance fluctuated by 65.99 tokens/second (217.8% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 3880.00 ms (high latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Feb 16, 2026, 09:00 AM based on 236 total samples.

Distribution of throughput measurements showing performance consistency across benchmark runs.

Historical performance trends showing how throughput has changed over the benchmarking period.

Provider	Model	Avg Toks/Sec	Min	Max	Avg TTF (ms)
deepinfra	Qwen 2.5 Coder 32B	30.30	1.01	67.00	3880.00

The latest rolling average throughput is 30.30 tokens per second with an average time to first token of 3880.00 ms across 236 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Feb 16, 2026, 09:00 AM.