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.
A local, Jev-compatible decision model from Rizzo AI Academy. XHToken's Spark-X2.5-4B with a merged typed-decisions LoRA, run on llama.cpp; yes/no, choice and score questions share one prefill of the state and are read from the answer-letter logits. No text is generated.
Decides
choice, noul, score
choice, score, noul, classify, route
Architecture
canopy-jev
rizzo-flow
Fine-tuned from
qwen/qwen3.8-27b
xhtoken/spark-x2.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.4%
64.8%
Calibration error
—
0.112
Valid action rate
—
—
Median latency
—
195 ms
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 rizzo-flow?
canopy-jev is from Ruoxi Qiu and rizzo-flow from Rizzo AI Academy. Both have open weights you can download and run. Both answer choice, noul and score questions. Only rizzo-flow answers classify and route. rizzo-flow is the smaller model, at 4.0B parameters to 27B.
Which is more accurate, canopy-jev or rizzo-flow?
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, rizzo-flow 64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0 — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, canopy-jev or rizzo-flow?
canopy-jev: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run canopy-jev or rizzo-flow locally?
Yes, both: systemone pull camellia86/canopy-jev and systemone pull rizzo-ai-academy/rizzo-flow download the weights.
Evaluation suite
JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
