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.
Invergent's decision model for text and images. A fine-tune of Gemma-4-26B-A4B (about 4B parameters active per token) that answers Choice, Noul and Score questions, with an optional thinking mode for harder questions.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
anyjev
rune
Fine-tuned from
qwen/qwen3-8b
google/gemma-4-26b-a4b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Invergent
Input price
—
—
Decision accuracy
77.1%
—
Calibration error
0.034
—
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 rune?
anyjev is from Nokia and rune from Surogate (Invergent). anyjev has open weights you can download and run; rune has open weights and a hosted API. Both answer choice, score, noul, classify and route questions. anyjev is the smaller model, at 8.0B parameters to 26B.
Which is more accurate, anyjev or rune?
Only anyjev publishes an accuracy figure (77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question); rune does not, so there is no comparison to make without your own test.
Which is cheaper, anyjev or rune?
anyjev: Free (open weights). rune: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or rune locally?
Yes, both: systemone pull nokia/anyjev and systemone pull surogate/rune download the weights.
Evaluation suite
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question