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.
Qwen3.5-4B with a merged rank-16 LoRA distilled from 17,408 teacher questions and 30,000 public training rows, read out as a temperature-scaled softmax over answer-letter logits. Also in 9B, 2B and GGUF.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
anyjev
jevk5
Fine-tuned from
qwen/qwen3-8b
qwen/qwen3.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.1%
78.4%
Calibration error
0.034
0.035
Valid action rate
—
—
Median latency
—
13.2 ms
p95 latency
—
—
Evaluation suite
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 jevk5?
anyjev is from Nokia Applied Research and jevk5 from Alibi Serikbay. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. jevk5 is the smaller model, at 4.0B parameters to 8.0B.
Which is more accurate, anyjev or jevk5?
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, jevk5 78.4% on JevBench public hard tier — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, anyjev or jevk5?
anyjev: Free (open weights). jevk5: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or jevk5 locally?
Yes, both: systemone pull nokia-applied-research/anyjev and systemone pull alibi-serikbay/jevk5 download the weights.
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
