Typed decisions from Google's frozen Gemma-4-12B-it, with no fine-tuning. A small shim over unmodified vLLM letters the options, reads the model's own probability for each letter at one answer position and applies one calibration temperature; one output token per decision.
An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
cygnet
kev
Fine-tuned from
google/gemma-4-12b-it
qwen/qwen3.5-4b-base
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.9%
83.8%
Calibration error
—
0.042
Valid action rate
—
—
Median latency
50 ms
—
p95 latency
—
—
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between cygnet and kev?
cygnet is from Blockbrain Labs and kev from Jared Palmer. Both have open weights you can download and run. Both answer choice, score and noul questions. Only kev answers classify and route. cygnet reads up to 16K tokens of state, against 8K tokens for kev. kev is the smaller model, at 4.0B parameters to 12B. cygnet is licensed mit; kev, apache-2.0.
Which is more accurate, cygnet or kev?
They report on different suites — cygnet 87.9% on JevBench public set (231 items), JevBench CLI, kev 83.8% on transfer-v4 (locked, out of domain) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cygnet or kev?
cygnet: Free (open weights). kev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run cygnet or kev locally?
Yes, both: systemone pull blockbrain-labs/cygnet and systemone pull jared-palmer/kev download the weights.
