llm-benchmarks
githubdrose.io

Qwen3.5 397B A17B Benchmarks


Measured on streamlake

909 runs
Avg Tokens / Second
10.00
Avg Time to First Token (ms)
7080.00
Runs Analysed
909
Last Updated
Sep 1, 2026, 04:06 PM

Throughput distribution

Throughput over time

Qwen3.5 397B A17Bvenice2tok/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 71 tok/s (99th percentile) · dashed rule is the model's own mean · 13 further providers not drawn · 1 samples above the ceiling drawn at it

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
streamlakeQwen3.5 397B A17B10.005.2712.407080.00

Frequently Asked Questions

How fast is Qwen3.5 397B A17B?
The latest rolling average throughput is 10.00 tokens per second with an average time to first token of 7080.00 ms across 909 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 PM.

Related models