An open System One model from Interfaze AI. A rank-32 LoRA on Qwen3.5-4B reads yes/no, choice and score answers from the logits of one forward pass, returns calibrated probabilities and serves the /v1/systemone API.
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
lev
nanojev
Fine-tuned from
qwen/qwen3.5-4b
qwen/qwen3-0.6b
License
apache-2.0
mit
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
68.9%
—
Calibration error
0.115
—
Valid action rate
—
—
Median latency
69 ms
—
p95 latency
—
—
Evaluation suite
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 lev and nanojev?
lev is from Interfaze AI and nanojev from TianyuCodings. Both have open weights you can download and run. Both answer choice, score and noul questions. Only lev answers classify and route. nanojev is the smaller model, at 600M parameters to 4.0B. lev is licensed apache-2.0; nanojev, mit.
Which is more accurate, lev or nanojev?
Only lev publishes an accuracy figure (68.9% on S1Bench (13 public subsets, macro)); nanojev does not, so there is no comparison to make without your own test.
Which is cheaper, lev or nanojev?
lev: Free (open weights). nanojev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run lev or nanojev locally?
Yes, both: systemone pull interfaze-ai/lev and systemone pull tianyu-codings/nanojev download the weights.
