llm-benchmarks
githubdrose.io

Qwen3 Coder 30B A3B Instruct Benchmarks


Measured on digitalocean

180 runs
Avg Tokens / Second
73.90
Avg Time to First Token (ms)
550.00
Runs Analysed
180
Last Updated
Sep 1, 2026, 04:08 AM

Throughput distribution

Throughput over time

Qwen3 Coder 30B A3B Instructsiliconflow1tok/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 · 6 further providers not drawn

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
digitaloceanQwen3 Coder 30B A3B Instruct73.9073.9073.90550.00

Frequently Asked Questions

How fast is Qwen3 Coder 30B A3B Instruct?
The latest rolling average throughput is 73.90 tokens per second with an average time to first token of 550.00 ms across 180 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, 04:08 AM.

Related models