Ruoxi Qiu's decision adapter for a frozen Qwen3.8-27B: a 6.3M-parameter LoRA on the last four text layers plus a numerical prior. One shared state feeds isolated question branches; each Choice, Noul or Score question returns probabilities with no generated tokens.
Omar (kouhxp)'s CPU decision model: a Qwen3.5-0.8B fine-tune shipped as GGUF for llama.cpp that answers yes/no, choice and score questions with a probability per option plus a 'none of these' reject probability, served by a local Jev-style HTTP runtime.
Decides
choice, noul, score
choice, score, noul, classify, route
Architecture
canopy-jev
gutsy
Fine-tuned from
qwen/qwen3.8-27b
qwen/qwen3.5-0.8b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.4%
73.2%
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 canopy-jev and gutsy?
canopy-jev is from Ruoxi Qiu and gutsy from Omar (kouhxp). Both have open weights you can download and run. Both answer choice, noul and score questions. Only gutsy answers classify and route. gutsy is the smaller model, at 800M parameters to 27B.
Which is more accurate, canopy-jev or gutsy?
They report on different suites — canopy-jev 87.4% on JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer, gutsy 73.2% on JevBench public set (231 items; 169 correct), the maker's own run with Q8_0 — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, canopy-jev or gutsy?
canopy-jev: Free (open weights). gutsy: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run canopy-jev or gutsy locally?
Yes, both: systemone pull camellia86/canopy-jev and systemone pull kouhxp/gutsy download the weights.
—
Evaluation suite
JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer
JevBench public set (231 items; 169 correct), the maker's own run with Q8_0
