llm-benchmarks
githubdrose.io

Fugu Ultra Benchmarks


Measured on sakanaai

2 runs
Avg Tokens / Second
7.11
Avg Time to First Token (ms)
13400.00
Runs Analysed
2
Last Updated
Aug 19, 2026, 02:33 PM

Throughput distribution

Throughput over time

Fugu Ultrasakanaai0tok/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 6 tok/s (99th percentile) · dashed rule is the model's own mean · 1 samples above the ceiling drawn at it

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
sakanaaiFugu Ultra7.116.008.2213400.00

Frequently Asked Questions

How fast is Fugu Ultra?
The latest rolling average throughput is 7.11 tokens per second with an average time to first token of 13400.00 ms across 2 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 19, 2026, 02:33 PM.

Related models