llm-benchmarks
githubdrose.io

nova-micro Benchmarks


Measured on bedrock

1362 runs
Avg Tokens / Second
120.00
Avg Time to First Token (ms)
310.00
Runs Analysed
1362
Last Updated
Aug 9, 2026, 04:52 PM

Throughput distribution

  • nova-micro bedrock120 tok/s
050100150

Visible-token throughput, same basis as the table · curves normalised per model

Throughput over time

nova-microbedrock118tok/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 180 tok/s (99th percentile) · dashed rule is the model's own mean

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
bedrocknova-micro120.0027.20188.00310.00

Frequently Asked Questions

How fast is nova-micro?
The latest rolling average throughput is 120.00 tokens per second with an average time to first token of 310.00 ms across 1362 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 9, 2026, 04:52 PM.

Related models