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.
Featherless AI's open server that turns a stock Hugging Face language model into a typed-decision endpoint. It reads the next-token logits for each question and builds the Choice, Score or Noul answer itself; no classifier head is trained and no JSON is generated.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
rizzo-flow
simple-jev
Fine-tuned from
xhtoken/spark-x2.5-4b
google/gemma-4-26b-a4b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Featherless AI
Input price
—
—
Decision accuracy
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 rizzo-flow and simple-jev?
rizzo-flow is from Rizzo AI Academy and simple-jev from Featherless AI. rizzo-flow has open weights you can download and run; simple-jev has open weights and a hosted API. Both answer choice, score, noul, classify and route questions.
Which is more accurate, rizzo-flow or simple-jev?
Only rizzo-flow publishes an accuracy figure (64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0); simple-jev does not, so there is no comparison to make without your own test.
Which is cheaper, rizzo-flow or simple-jev?
rizzo-flow: Free (open weights). simple-jev: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run rizzo-flow or simple-jev locally?
Yes, both: systemone pull rizzo-ai-academy/rizzo-flow and systemone pull featherless-ai/simple-jev download the weights.
—
Evaluation suite
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
