The flagship of the vLLM Semantic Router team's Decision 1.0 family. Qwen3.5-9B with a shared candidate head returns a probability for every supplied answer to choice, yes/no and score questions, over a 16,384-token input.
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
decision
nanojev
Fine-tuned from
qwen/qwen3.5-9b
qwen/qwen3-0.6b
License
apache-2.0
mit
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.4%
—
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 decision and nanojev?
decision is from vLLM Semantic Router and nanojev from TianyuCodings. Both have open weights you can download and run. Both answer choice, score and noul questions. Only decision answers classify and route. nanojev is the smaller model, at 600M parameters to 9.0B. decision is licensed apache-2.0; nanojev, mit.
Which is more accurate, decision or nanojev?
Only decision publishes an accuracy figure (77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted)); nanojev does not, so there is no comparison to make without your own test.
Which is cheaper, decision or nanojev?
decision: Free (open weights). nanojev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decision or nanojev locally?
Yes, both: systemone pull vllm-semantic-router/decision and systemone pull tianyu-codings/nanojev download the weights.
