An open Jev-style decision model by Andy Zhang: a LoRA adapter on Gemma 4 26B-A4B (also on Gemma 4 12B) that reads a state and returns a temperature-calibrated probability for every option of a yes/no, choice or score question in one forward pass.
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
ajev
kev
Fine-tuned from
google/gemma-4-26b-a4b-it
qwen/qwen3.5-4b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
83.8%
Calibration error
—
0.042
Valid action rate
—
—
Median latency
49 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 ajev and kev?
ajev is from Andy Zhang 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. kev is the smaller model, at 4.0B parameters to 26B.
Which is more accurate, ajev or kev?
Only kev publishes an accuracy figure (83.8% on transfer-v4 (locked, out of domain)); ajev does not, so there is no comparison to make without your own test.
Which is cheaper, ajev or kev?
ajev: Free (open weights). kev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run ajev or kev locally?
Yes, both: systemone pull andy-zhang/ajev and systemone pull jared-palmer/kev download the weights.
