An embedding model turned decision model. Qwen3-Embedding-4B with a merged LoRA, driven by the open JevEmbed toolkit, which scores Choice, Score and Noul questions from embedding similarity and returns a distribution without generating text.
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
choice, score, noul
Architecture
jevembed
startlux-decision
Fine-tuned from
qwen/qwen3-embedding-4b
—
License
apache-2.0
cc-by-nc-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
85.9%
88.3%
Calibration error
—
—
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 jevembed and startlux-decision?
jevembed is from HIT-TMG (Lychee Team) and startlux-decision from StartLux. Both have open weights you can download and run. Both answer choice, score and noul questions. Only jevembed answers classify. jevembed is the smaller model, at 4.0B parameters to 4.7B. jevembed is licensed apache-2.0; startlux-decision, cc-by-nc-4.0.
Which is more accurate, jevembed or startlux-decision?
They report on different suites — jevembed 85.9% on JevEmbed-Data test split (64,110 hard-label questions), final LoRA checkpoint before merging, 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, jevembed or startlux-decision?
jevembed: Free (open weights). startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jevembed or startlux-decision locally?
Yes, both: systemone pull hit-tmg/jevembed and systemone pull startlux/startlux-decision download the weights.
Evaluation suite
JevEmbed-Data test split (64,110 hard-label questions), final LoRA checkpoint before merging
JevBench public set (231 items; 204 correct), maker's run
