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.
A Gemma 4 12B fine-tune for typed decisions that also chats and reads images. Ships as GGUF for llama.cpp, holds a 64K context on a 16 GB GPU, and serves /v1/systemone next to /v1/chat/completions.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
anyjev
winnow
Fine-tuned from
qwen/qwen3-8b
google/gemma-4-12b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.1%
85.7%
Calibration error
0.034
—
Valid action rate
—
—
Median latency
—
143 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 winnow?
anyjev is from Nokia Applied Research and winnow from EldanRing. 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 12B.
Which is more accurate, anyjev or winnow?
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, winnow 85.7% on JevBench public subset (231 items), Q8_0 — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, anyjev or winnow?
anyjev: Free (open weights). winnow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or winnow locally?
Yes, both: systemone pull nokia-applied-research/anyjev and systemone pull eldanring/winnow download the weights.
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
