Hanno Labs' small calibrated decision model. A LoRA on Qwen3-1.7B plus trained decision-token embeddings with stable slots, returning the full distribution over up to 255 caller-defined choices and a null slot for Choice, Score and Noul questions.
StartLux's decision family in five sizes, 0.8B to 27B. All questions in a request are answered in one forward pass, with a probability for every option, through a TypeSafe /v1/systemone-compatible server that records CUDA graphs for short requests.
Decides
choice, score, noul, classify, route
choice, score, noul
Architecture
bosun
startlux-decision
Fine-tuned from
qwen/qwen3-1.7b
—
License
apache-2.0
cc-by-nc-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
84.9%
88.3%
Calibration error
0.050
—
Valid action rate
—
—
Median latency
—
26 ms
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 bosun and startlux-decision?
bosun is from Hanno Labs and startlux-decision from StartLux. Both have open weights you can download and run. Both answer choice, score and noul questions. Only bosun answers classify and route. bosun is the smaller model, at 2.0B parameters to 4.7B. bosun is licensed apache-2.0; startlux-decision, cc-by-nc-4.0.
Which is more accurate, bosun or startlux-decision?
They report on different suites — bosun 84.9% on DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families), startlux-decision 88.3% on JevBench public set (231 items; 204 correct), maker's run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bosun or startlux-decision?
bosun: Free (open weights). startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bosun or startlux-decision locally?
Yes, both: systemone pull hanno-labs/bosun and systemone pull startlux/startlux-decision download the weights.
Evaluation suite
DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families)
JevBench public set (231 items; 204 correct), maker's run
