Frontier Infra's open decision model. A LoRA merged into Qwen3.8-27B (thinking off) that answers one typed question per forward pass with a probability over the option labels, served through AINode's TypeSafe-compatible /v1/systemone.
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.
Decides
choice, score, noul, classify, route
choice, score, noul, classify
Architecture
jebadiah
jevembed
Fine-tuned from
qwen/qwen3.8-27b
qwen/qwen3-embedding-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
86.6%
85.9%
Calibration error
0.113
—
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 jebadiah and jevembed?
jebadiah is from Frontier Infra and jevembed from HIT-TMG (Lychee Team). Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only jebadiah answers route. jevembed is the smaller model, at 4.0B parameters to 27B.
Which is more accurate, jebadiah or jevembed?
They report on different suites — jebadiah 86.6% on JevBench public set (231 items), maker's run with the v1.4.2 harness; ECE on the hard tier, jevembed 85.9% on JevEmbed-Data test split (64,110 hard-label questions), final LoRA checkpoint before merging — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, jebadiah or jevembed?
jebadiah: Free (open weights). jevembed: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jebadiah or jevembed locally?
Yes, both: systemone pull frontier-infra/jebadiah and systemone pull hit-tmg/jevembed download the weights.
Evaluation suite
JevBench public set (231 items), maker's run with the v1.4.2 harness; ECE on the hard tier
JevEmbed-Data test split (64,110 hard-label questions), final LoRA checkpoint before merging
