llm-benchmarks
githubdrose.io

Qwen2.5 Coder 32B Instruct Benchmarks


Measured on cloudflare

41 runs
Avg Tokens / Second
24.70
Avg Time to First Token (ms)
710.00
Runs Analysed
41
Last Updated
Sep 1, 2026, 04:06 AM

Throughput distribution

Throughput over time

Qwen2.5 Coder 32B Instructcloudflare1tok/s

Generated throughput, including reasoning tokens — so a thinking model's line does not collapse; the table ranks on visible tokens · one cell per model, showing its best-covered provider · shared vertical scale, 0 to 28 tok/s (99th percentile) · dashed rule is the model's own mean · 1 further provider not drawn

Every provider serving this model

2 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
cloudflareQwen2.5 Coder 32B Instruct25.3023.8026.30610.00
cloudflareQwen2.5 Coder 32B Instruct24.1016.7027.10810.00

Frequently Asked Questions

How fast is Qwen2.5 Coder 32B Instruct?
The latest rolling average throughput is 24.70 tokens per second with an average time to first token of 710.00 ms across 41 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 1, 2026, 04:06 AM.

Related models