An embedding model turned decision model. Qwen3-Embedding-4B with a merged LoRA, driven by the open JevEmbed toolkit, which scores Choice, Score and Noul questions from embedding similarity and returns a distribution without generating text.
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, classify
choice, score, noul, classify, route
Architecture
jevembed
neohorse
Fine-tuned from
qwen/qwen3-embedding-4b
tokenrhythm/neohorse-1-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
85.9%
75.3%
Calibration error
—
—
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 jevembed and neohorse-jev?
jevembed is from HIT-TMG (Lychee Team) and neohorse-jev from TokenRhythm. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only neohorse-jev answers route.
Which is more accurate, jevembed or neohorse-jev?
They report on different suites — jevembed 85.9% on JevEmbed-Data test split (64,110 hard-label questions), final LoRA checkpoint before merging, 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, jevembed or neohorse-jev?
jevembed: Free (open weights). neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jevembed or neohorse-jev locally?
Yes, both: systemone pull hit-tmg/jevembed and systemone pull tokenrhythm/neohorse-jev download the weights.
—
Evaluation suite
JevEmbed-Data test split (64,110 hard-label questions), final LoRA checkpoint before merging
JevBench public set (231 items), vLLM, maker's run
