AutoTrust's student of TypeSafe Jev 1.13. A frozen Qwen3.8-27B plus a 108.9M-parameter decision block trained on Jev's own output distributions; one set of weights answers typed questions in one pass (System 1) or generates text with the untouched base (System 2).
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
choice, score, noul, classify, route
Architecture
blocks-of-experts
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
88.7%
64.8%
Calibration error
—
0.112
Valid action rate
—
—
Median latency
137 ms
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 jev-27b and rizzo-flow?
jev-27b is from AutoTrust AI Lab and rizzo-flow from Rizzo AI Academy. Both have open weights you can download and run. Both answer choice, score and noul questions. Only rizzo-flow answers classify and route. rizzo-flow is the smaller model, at 4.0B parameters to 27B.
Which is more accurate, jev-27b or rizzo-flow?
They report on different suites — jev-27b 88.7% on JevBench public set (231 items), family-macro score, maker's run, 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-27b or rizzo-flow?
jev-27b: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, jev-27b or rizzo-flow?
By their publishers’ figures, jev-27b answers in about 137 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-27b or rizzo-flow locally?
Yes, both: systemone pull autotrust-ai/jev-27b and systemone pull rizzo-ai-academy/rizzo-flow download the weights.
Evaluation suite
JevBench public set (231 items), family-macro score, maker's run
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
