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.
FrontiersMind's decision model on a base it pre-trained from scratch. Each question reads the state and its own tokens once and a 256-dimension pointer head scores the options; Choice and Score take up to 255 entries, and nothing is generated.
Decides
choice, score, noul
choice, score, noul
Architecture
ajev
lumma-fev
Fine-tuned from
google/gemma-4-26b-a4b-it
frontiersmind/lumma-0.6b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
64.0%
Calibration error
—
—
Valid action rate
—
—
Median latency
49 ms
45.8 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 lumma-fev?
ajev is from Andy Zhang and lumma-fev from FrontiersMind. Both have open weights you can download and run. Both answer choice, score and noul questions. lumma-fev is the smaller model, at 649M parameters to 26B.
Which is more accurate, ajev or lumma-fev?
Only lumma-fev publishes an accuracy figure (64.0% on typed-decisions (maker's table; split not stated)); ajev does not, so there is no comparison to make without your own test.
Which is cheaper, ajev or lumma-fev?
ajev: Free (open weights). lumma-fev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, ajev or lumma-fev?
By their publishers’ figures, lumma-fev answers in about 45.8 ms at the median and ajev in about 49 ms — measured on different hardware, so treat it as a rough guide.
Can I run ajev or lumma-fev locally?
Yes, both: systemone pull andy-zhang/ajev and systemone pull frontiersmind/lumma-fev download the weights.
