SimpleJev's LoRA adapters and pointer head that turn an open model into a typed-decision model: given a state, a question and the options, it returns a probability for every option without generating text. This entry is the Qwen3.8-27B release; the others are linked.
TokenRhythm's prefill-only decision model for agent workflows. Built on its NeoHorse-1-4B (a Qwen3.5-4B derivative), it predicts Choice, Noul and Score answers over application-defined options without generating text, with optional single-image input.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
jevany
neohorse
Fine-tuned from
qwen/qwen3.8-27b
tokenrhythm/neohorse-1-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
86.0%
75.3%
Calibration error
0.026
—
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 jevany and neohorse-jev?
jevany is from SimpleJev and neohorse-jev from TokenRhythm. Both have open weights you can download and run. Both answer choice, score and noul questions. Only neohorse-jev answers classify and route. neohorse-jev is the smaller model, at 4.0B parameters to 27B.
Which is more accurate, jevany or neohorse-jev?
They report on different suites — jevany 86.0% on SimpleJev Transfer suite (1,046 decisions from seven cross-domain datasets plus robustness slices; the maker's own), neohorse-jev 75.3% on JevBench public set (231 items), vLLM, maker's run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, jevany or neohorse-jev?
jevany: Free (open weights). neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jevany or neohorse-jev locally?
Yes, both: systemone pull simplejev/jevany and systemone pull tokenrhythm/neohorse-jev download the weights.
Evaluation suite
SimpleJev Transfer suite (1,046 decisions from seven cross-domain datasets plus robustness slices; the maker's own)
JevBench public set (231 items), vLLM, maker's run
