A training-free layer that turns an open LLM into a decision model. It reads typed choice, yes/no and score answers from one prefill, removes option-order bias with no labels and, from a few hundred labels, calibrates or fits a closed-form head. Weights stay untouched.
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, score, noul, classify, route
choice, noul, score
Architecture
anyjev
nanojev
Fine-tuned from
qwen/qwen3-8b
qwen/qwen3-0.6b
License
apache-2.0
mit
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.1%
—
Calibration error
0.034
—
Valid action rate
—
—
Median latency
—
—
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 anyjev and nanojev?
anyjev is from Nokia Applied Research and nanojev from TianyuCodings. Both have open weights you can download and run. Both answer choice, score and noul questions. Only anyjev answers classify and route. nanojev is the smaller model, at 600M parameters to 8.0B. anyjev is licensed apache-2.0; nanojev, mit.
Which is more accurate, anyjev or nanojev?
Only anyjev publishes an accuracy figure (77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question); nanojev does not, so there is no comparison to make without your own test.
Which is cheaper, anyjev or nanojev?
anyjev: Free (open weights). nanojev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or nanojev locally?
Yes, both: systemone pull nokia-applied-research/anyjev and systemone pull tianyu-codings/nanojev download the weights.
—
Evaluation suite
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
