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.
Together AI's Jev-style classifier. A LoRA fine-tune of Qwen3.5-4B that reads a state, a question and 2 to 24 options and returns one option letter. Served on Together's platform; recipe published.
Decides
choice, noul, score
choice, classify, route
Architecture
nanojev
tev
Fine-tuned from
qwen/qwen3-0.6b
qwen/qwen3.5-4b
License
mit
Unspecified — weights licence being finalised
Availability
Open weights
Open weights + hosted API
Hosted by
—
Together AI
Input price
—
$0.042/MTok
Decision accuracy
—
88.0%
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 nanojev and tev1?
nanojev is from TianyuCodings and tev1 from Together AI. nanojev has open weights you can download and run; tev1 has open weights and a hosted API. Both answer choice questions. Only nanojev answers noul and score. Only tev1 answers classify and route. nanojev is the smaller model, at 600M parameters to 4.0B. nanojev is licensed mit; tev1, other.
Which is more accurate, nanojev or tev1?
Only tev1 publishes an accuracy figure (88.0% on Together development set (reused, not held out)); nanojev does not, so there is no comparison to make without your own test.
Which is cheaper, nanojev or tev1?
nanojev: Free (open weights). tev1: $0.042 / $0 per 1M, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run nanojev or tev1 locally?
Yes, both: systemone pull tianyu-codings/nanojev and systemone pull together-ai/tev1 download the weights.
