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.
A 4B decision model fine-tuned from Qwen3.5-4B-Base. A state and typed questions (choice, yes/no, score) go in; a temperature-calibrated probability for every option comes out of one pass, through a self-hosted /v1/systemone-compatible server. Apache-2.0 weights and code.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
neohorse
wald
Fine-tuned from
tokenrhythm/neohorse-1-4b
qwen/qwen3.5-4b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
75.3%
88.3%
Calibration error
—
0.045
Valid action rate
—
—
Median latency
—
33 ms
p95 latency
—
168 ms
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 neohorse-jev and wald?
neohorse-jev is from TokenRhythm and wald from ORG2 AI. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. neohorse-jev is the smaller model, at 4.0B parameters to 4.2B.
Which is more accurate, neohorse-jev or wald?
They report on different suites — neohorse-jev 75.3% on JevBench public set (231 items), vLLM, maker's run, wald 88.3% on JevBench public set (231 items; 204 correct), maker's run with the JevBench CLI, v1.2, effort none; items used as a development scoreboard — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, neohorse-jev or wald?
neohorse-jev: Free (open weights). wald: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run neohorse-jev or wald locally?
Yes, both: systemone pull tokenrhythm/neohorse-jev and systemone pull org2ai/wald download the weights.
Evaluation suite
JevBench public set (231 items), vLLM, maker's run
JevBench public set (231 items; 204 correct), maker's run with the JevBench CLI, v1.2, effort none; items used as a development scoreboard
