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.
A ModernBERT-large encoder with an option-marker head. Premise and options are packed into one sequence and each option's marker is scored in a single bidirectional pass; version 1.2 makes the scoring order-invariant.
Decides
choice, score, noul, classify, route
choice, score, noul, classify
Architecture
kev
von
Fine-tuned from
qwen/qwen3.5-4b-base
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
83.8%
63.9%
Calibration error
0.042
0.045
Valid action rate
—
—
Median latency
—
18 ms
p95 latency
—
—
Evaluation suite
transfer-v4 (locked, out of domain)
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 kev and von?
kev is from Jared Palmer and von from wfzyx. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only kev answers route. von is the smaller model, at 395M parameters to 4.0B.
Which is more accurate, kev or von?
They report on different suites — kev 83.8% on transfer-v4 (locked, out of domain), von 63.9% on JevBench public standard tier — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, kev or von?
kev: Free (open weights). von: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run kev or von locally?
Yes, both: systemone pull jared-palmer/kev and systemone pull wfzyx/von download the weights.
