llm-benchmarks
githubdrose.io

Qwen3 Next 80B A3B Instruct Benchmarks


Measured on novita

46 runs
Avg Tokens / Second
44.80
Avg Time to First Token (ms)
1010.00
Runs Analysed
46
Last Updated
Sep 1, 2026, 04:05 AM

Throughput distribution

Throughput over time

Qwen3 Next 80B A3B Instructalibaba1tok/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 54 tok/s (99th percentile) · dashed rule is the model's own mean · 5 further providers not drawn

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
novitaQwen3 Next 80B A3B Instruct44.8024.6055.601010.00

Frequently Asked Questions

How fast is Qwen3 Next 80B A3B Instruct?
The latest rolling average throughput is 44.80 tokens per second with an average time to first token of 1010.00 ms across 46 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, 04:05 AM.

Related models