The most-downloaded open System One reproduction. Merged Qwen3.5 fine-tunes, trained on about 95 public decision sets, then calibration-aware RL and a rank-64 LoRA, that softmax letter logits at an answer slot.
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, classify, route
choice, score, noul, classify, route
Architecture
decider
kev
Fine-tuned from
qwen/qwen3.5-2b-base
qwen/qwen3.5-4b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
80.2%
83.8%
Calibration error
0.038
0.042
Valid action rate
—
—
Median latency
3.2 ms
—
p95 latency
—
—
Evaluation suite
Decider 67-task regression set
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 decider and kev?
decider is from Mapika and kev from Jared Palmer. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. decider is the smaller model, at 2.0B parameters to 4.0B.
Which is more accurate, decider or kev?
They report on different suites — decider 80.2% on Decider 67-task regression set, 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, decider or kev?
decider: Free (open weights). kev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decider or kev locally?
Yes, both: systemone pull mapika/decider and systemone pull jared-palmer/kev download the weights.
