llm-benchmarks
githubdrose.io

Hunyuan A13B Instruct Benchmarks


Measured on siliconflow

41 runs
Avg Tokens / Second
28.75
Avg Time to First Token (ms)
2815.00
Runs Analysed
41
Last Updated
Sep 1, 2026, 04:08 AM

Throughput distribution

Throughput over time

Hunyuan A13B 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 40 tok/s (99th percentile) · dashed rule is the model's own mean · 1 further provider not drawn · 1 samples above the ceiling drawn at it

Every provider serving this model

2 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
siliconflowHunyuan A13B Instruct28.405.2537.803760.00
siliconflowHunyuan A13B Instruct29.105.1242.901870.00

Frequently Asked Questions

How fast is Hunyuan A13B Instruct?
The latest rolling average throughput is 28.75 tokens per second with an average time to first token of 2815.00 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, 04:08 AM.

Related models