A training-free layer that turns an open LLM into a decision model. It reads typed choice, yes/no and score answers from one prefill, removes option-order bias with no labels and, from a few hundred labels, calibrates or fits a closed-form head. Weights stay untouched.
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.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
anyjev
jebadiah
Fine-tuned from
qwen/qwen3-8b
qwen/qwen3.8-27b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.1%
86.6%
Calibration error
0.034
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 anyjev and jebadiah?
anyjev is from Nokia and jebadiah from Frontier Infra. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. anyjev is the smaller model, at 8.0B parameters to 27B.
Which is more accurate, anyjev or jebadiah?
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, jebadiah 86.6% on JevBench public set (231 items), maker's run with the v1.4.2 harness; ECE on the hard tier — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, anyjev or jebadiah?
anyjev: Free (open weights). jebadiah: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or jebadiah locally?
Yes, both: systemone pull nokia/anyjev and systemone pull frontier-infra/jebadiah download the weights.
Evaluation suite
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
JevBench public set (231 items), maker's run with the v1.4.2 harness; ECE on the hard tier
