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.
DecisionTune's 395M decision model: ModernBERT-large fine-tuned with a 4 KB scoring head that scores a marker per option, answering a choice or yes/no question in one encoder pass with a probability for every option. Runs locally on CPU or GPU via PyTorch, MLX or ONNX.
Decides
choice, score, noul
choice, noul, route, classify
Architecture
ajev
decisiontune
Fine-tuned from
google/gemma-4-26b-a4b-it
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
—
Calibration error
—
—
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 decisiontune?
ajev is from Andy Zhang and decisiontune from DecisionTune. Both have open weights you can download and run. Both answer choice and noul questions. Only ajev answers score. Only decisiontune answers route and classify. decisiontune is the smaller model, at 395M parameters to 26B.
Which is more accurate, ajev or decisiontune?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, ajev or decisiontune?
ajev: Free (open weights). decisiontune: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run ajev or decisiontune locally?
Yes, both: systemone pull andy-zhang/ajev and systemone pull decision-tune/decisiontune download the weights.
