llm-benchmarks
githubdrose.io

Qwen3 30B A3B Instruct 2507 Benchmarks


Measured on alibaba

56 runs
Avg Tokens / Second
49.30
Avg Time to First Token (ms)
650.00
Runs Analysed
56
Last Updated
Sep 1, 2026, 03:09 AM

Throughput distribution

Throughput over time

Qwen3 30B A3B Instruct 2507streamlake1tok/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 37 tok/s (99th percentile) · dashed rule is the model's own mean · 7 further providers not drawn

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
alibabaQwen3 30B A3B Instruct 250749.3046.9053.80650.00

Frequently Asked Questions

How fast is Qwen3 30B A3B Instruct 2507?
The latest rolling average throughput is 49.30 tokens per second with an average time to first token of 650.00 ms across 56 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, 03:09 AM.

Related models