llm-benchmarks
githubdrose.io

Morph V3 Fast Benchmarks


Measured on morph

40 runs
Avg Tokens / Second
22.40
Avg Time to First Token (ms)
745.00
Runs Analysed
40
Last Updated
Sep 1, 2026, 04:05 AM

Throughput distribution

Throughput over time

Morph V3 Fastmorph1tok/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 28 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)
morphMorph V3 Fast28.2022.9038.80500.00
morphMorph V3 Fast16.608.0762.00990.00

Frequently Asked Questions

How fast is Morph V3 Fast?
The latest rolling average throughput is 22.40 tokens per second with an average time to first token of 745.00 ms across 40 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