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 149.6M ModernBERT-base cross-encoder with a scalar head that picks an agent's next action or tool from labels and descriptions you supply. Each option is scored against the state and a softmax ranks the set; no text is generated. Experimental preview, not calibrated.
Decides
choice, score, noul, classify, route
choice, rank, route
Architecture
kev
modernjev
Fine-tuned from
qwen/qwen3.5-4b-base
answerdotai/modernbert-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
83.8%
73.4%
Calibration error
0.042
—
Valid action rate
—
—
Median latency
—
—
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 kev and modernjev-decide?
kev is from Jared Palmer and modernjev-decide from Maziyar Panahi. Both have open weights you can download and run. Both answer choice and route questions. Only kev answers score, noul and classify. Only modernjev-decide answers rank. kev reads up to 8K tokens of state, against 4K tokens for modernjev-decide. modernjev-decide is the smaller model, at 150M parameters to 4.0B.
Which is more accurate, kev or modernjev-decide?
They report on different suites — kev 83.8% on transfer-v4 (locked, out of domain), modernjev-decide 73.4% on AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, kev or modernjev-decide?
kev: Free (open weights). modernjev-decide: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run kev or modernjev-decide locally?
Yes, both: systemone pull jared-palmer/kev and systemone pull maziyar-panahi/modernjev-decide download the weights.
—
Evaluation suite
transfer-v4 (locked, out of domain)
AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split)