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.
FrontiersMind's decision model on a base it pre-trained from scratch. Each question reads the state and its own tokens once and a 256-dimension pointer head scores the options; Choice and Score take up to 255 entries, and nothing is generated.
Decides
choice, score, noul, classify, route
choice, score, noul
Architecture
anyjev
lumma-fev
Fine-tuned from
qwen/qwen3-8b
frontiersmind/lumma-0.6b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.1%
64.0%
Calibration error
0.034
—
Valid action rate
—
—
Median latency
—
45.8 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 anyjev and lumma-fev?
anyjev is from Nokia and lumma-fev from FrontiersMind. Both have open weights you can download and run. Both answer choice, score and noul questions. Only anyjev answers classify and route. lumma-fev is the smaller model, at 649M parameters to 8.0B.
Which is more accurate, anyjev or lumma-fev?
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, lumma-fev 64.0% on typed-decisions (maker's table; split not stated) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, anyjev or lumma-fev?
anyjev: Free (open weights). lumma-fev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or lumma-fev locally?
Yes, both: systemone pull nokia/anyjev and systemone pull frontiersmind/lumma-fev download the weights.
Evaluation suite
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
