An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint.
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
kev
nanojev
Fine-tuned from
qwen/qwen3.5-4b-base
qwen/qwen3-0.6b
License
apache-2.0
mit
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
83.8%
—
Calibration error
0.042
—
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 kev and nanojev?
kev is from Jared Palmer and nanojev from TianyuCodings. Both have open weights you can download and run. Both answer choice, score and noul questions. Only kev answers classify and route. nanojev is the smaller model, at 600M parameters to 4.0B. kev is licensed apache-2.0; nanojev, mit.
Which is more accurate, kev or nanojev?
Only kev publishes an accuracy figure (83.8% on transfer-v4 (locked, out of domain)); nanojev does not, so there is no comparison to make without your own test.
Which is cheaper, kev or nanojev?
kev: Free (open weights). nanojev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run kev or nanojev locally?
Yes, both: systemone pull jared-palmer/kev and systemone pull tianyu-codings/nanojev download the weights.
