A rank-16 LoRA on Qwen3.5-4B built for the JevBench setting. A document, a policy and a question go in; a calibrated distribution over the option letters comes out of one forward pass. Research and demo use only.
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, score, noul, classify
choice, score, noul, classify, route
Architecture
hopper
rizzo-flow
Fine-tuned from
qwen/qwen3.5-4b
xhtoken/spark-x2.5-4b
License
Research and demo use only (training data includes RACE, non-commercial); serving code Apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
68.5%
64.8%
Calibration error
0.102
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 hopper and rizzo-flow?
hopper is from HopitAI and rizzo-flow from Rizzo AI Academy. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only rizzo-flow answers route. hopper is licensed other; rizzo-flow, apache-2.0.
Which is more accurate, hopper or rizzo-flow?
They report on different suites — hopper 68.5% on JevBench public hard tier (111 items, measured by the authors), 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, hopper or rizzo-flow?
hopper: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run hopper or rizzo-flow locally?
Yes, both: systemone pull hopit-ai/hopper and systemone pull rizzo-ai-academy/rizzo-flow download the weights.
—
Evaluation suite
JevBench public hard tier (111 items, measured by the authors)
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
