An open System One model from Interfaze AI. A rank-32 LoRA on Qwen3.5-4B reads yes/no, choice and score answers from the logits of one forward pass, returns calibrated probabilities and serves the /v1/systemone API.
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, route
choice, score, noul, classify, route
Architecture
lev
rizzo-flow
Fine-tuned from
qwen/qwen3.5-4b
xhtoken/spark-x2.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
68.9%
64.8%
Calibration error
0.115
0.112
Valid action rate
—
—
Median latency
69 ms
195 ms
p95 latency
—
—
Evaluation suite
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 lev and rizzo-flow?
lev is from Interfaze AI and rizzo-flow from Rizzo AI Academy. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions.
Which is more accurate, lev or rizzo-flow?
They report on different suites — lev 68.9% on S1Bench (13 public subsets, macro), 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, lev or rizzo-flow?
lev: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, lev or rizzo-flow?
By their publishers’ figures, lev answers in about 69 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 lev or rizzo-flow locally?
Yes, both: systemone pull interfaze-ai/lev and systemone pull rizzo-ai-academy/rizzo-flow download the weights.
S1Bench (13 public subsets, macro)
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
