StartLux's decision family in six sizes, 0.8B to a 35B-A3B mixture of experts. All questions in a request are answered in one forward pass, with a probability for every option, through a TypeSafe /v1/systemone-compatible server. Text, JSON or images, up to 256K tokens.
A 4B decision model fine-tuned from Qwen3.5-4B-Base. A state and typed questions (choice, yes/no, score) go in; a temperature-calibrated probability for every option comes out of one pass, through a self-hosted /v1/systemone-compatible server. Apache-2.0 weights and code.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
startlux-decision
wald
Fine-tuned from
—
qwen/qwen3.5-4b-base
License
cc-by-nc-4.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
88.3%
88.3%
Calibration error
—
0.045
Valid action rate
—
—
Median latency
26 ms
33 ms
p95 latency
—
168 ms
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 startlux-decision and wald?
startlux-decision is from StartLux and wald from ORG2 AI. Both have open weights you can download and run. Both answer choice, score and noul questions. Only wald answers classify and route. startlux-decision reads up to 256K tokens of state, against 128K tokens for wald. wald is the smaller model, at 4.2B parameters to 4.7B. startlux-decision is licensed cc-by-nc-4.0; wald, apache-2.0.
Which is more accurate, startlux-decision or wald?
They report on different suites — startlux-decision 88.3% on JevBench public set (231 items; 204 correct), maker's run, wald 88.3% on JevBench public set (231 items; 204 correct), maker's run with the JevBench CLI, v1.2, effort none; items used as a development scoreboard — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, startlux-decision or wald?
startlux-decision: Free (open weights). wald: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, startlux-decision or wald?
By their publishers’ figures, startlux-decision answers in about 26 ms at the median and wald in about 33 ms — measured on different hardware, so treat it as a rough guide.
Can I run startlux-decision or wald locally?
Yes, both: systemone pull startlux/startlux-decision and systemone pull org2ai/wald download the weights.
Evaluation suite
JevBench public set (231 items; 204 correct), maker's run
JevBench public set (231 items; 204 correct), maker's run with the JevBench CLI, v1.2, effort none; items used as a development scoreboard
Latest version
2026.10
1.2.0
Variants
LICENSE, NOTICE, startlux_decision
Dockerfile, LICENSE, NOTICE, model-files, reference, server
