A multimodal decision classifier over text, image, audio and video on Gemma 4 12B, fine-tuned on 30,000 questions. Returns a probability per option and generates nothing.
A 0.6B replica of the System One idea trained on game environments. A Qwen3-0.6B backbone with an attention-based Choice head that scores a dynamic candidate set for Maze, Snake, ViZDoom and position prediction, shipped with its full training pipeline.
Decides
choice, noul, score, classify
choice, noul, score
Architecture
jev-omni
nanojev
Fine-tuned from
google/gemma-4-12b-it
qwen/qwen3-0.6b
License
apache-2.0
mit
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.6%
—
Calibration error
0.040
—
Valid action rate
—
—
Median latency
83 ms
—
p95 latency
—
—
Evaluation suite
DecisionBench Medium (author's 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 jev-omni and nanojev?
jev-omni is from akhilaaa3 and nanojev from TianyuCodings. Both have open weights you can download and run. Both answer choice, noul and score questions. Only jev-omni answers classify. nanojev is the smaller model, at 600M parameters to 12B. jev-omni is licensed apache-2.0; nanojev, mit.
Which is more accurate, jev-omni or nanojev?
Only jev-omni publishes an accuracy figure (87.6% on DecisionBench Medium (author's set)); nanojev does not, so there is no comparison to make without your own test.
Which is cheaper, jev-omni or nanojev?
jev-omni: Free (open weights). nanojev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jev-omni or nanojev locally?
Yes, both: systemone pull akhilaaa3/jev-omni and systemone pull tianyu-codings/nanojev download the weights.
