A 2.8 MB byte-level transformer for GUI form filling. For each form element it returns one probability per typed option (fill an entity, check, click or skip), using jevlike's option-attention head.
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
choice, noul, score
Architecture
cua-s1
nanojev
Fine-tuned from
—
qwen/qwen3-0.6b
License
mit
mit
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
100.0%
—
Calibration error
—
—
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 cua-s1-forms and nanojev?
cua-s1-forms is from Cua and nanojev from TianyuCodings. Both have open weights you can download and run. Both answer choice questions. Only nanojev answers noul and score. cua-s1-forms is the smaller model, at 706K parameters to 600M.
Which is more accurate, cua-s1-forms or nanojev?
Only cua-s1-forms publishes an accuracy figure (100.0% on 196-decision evaluation on real forms); nanojev does not, so there is no comparison to make without your own test.
Which is cheaper, cua-s1-forms or nanojev?
cua-s1-forms: Free (open weights). nanojev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run cua-s1-forms or nanojev locally?
Yes, both: systemone pull cua/cua-s1-forms and systemone pull tianyu-codings/nanojev download the weights.
