A multimodal decision classifier over text, image, audio and video on Gemma 4 12B, fine-tuned on 30,000 questions. Returns a probability per option and generates nothing.
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, classify
choice, score, noul, classify, route
Architecture
jev-omni
rizzo-flow
Fine-tuned from
google/gemma-4-12b-it
xhtoken/spark-x2.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.6%
64.8%
Calibration error
0.040
0.112
Valid action rate
—
—
Median latency
83 ms
195 ms
p95 latency
—
—
Evaluation suite
DecisionBench Medium (author's set)
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 jev-omni and rizzo-flow?
jev-omni is from akhilaaa3 and rizzo-flow from Rizzo AI Academy. Both have open weights you can download and run. Both answer choice, noul, score and classify questions. Only rizzo-flow answers route. rizzo-flow is the smaller model, at 4.0B parameters to 12B.
Which is more accurate, jev-omni or rizzo-flow?
They report on different suites — jev-omni 87.6% on DecisionBench Medium (author's set), 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, jev-omni or rizzo-flow?
jev-omni: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, jev-omni or rizzo-flow?
By their publishers’ figures, jev-omni answers in about 83 ms at the median and rizzo-flow in about 195 ms — measured on different hardware, so treat it as a rough guide.
Can I run jev-omni or rizzo-flow locally?
Yes, both: systemone pull akhilaaa3/jev-omni and systemone pull rizzo-ai-academy/rizzo-flow download the weights.
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
