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.
Together AI's Jev-style classifier. A LoRA fine-tune of Qwen3.5-4B that reads a state, a question and 2 to 24 options and returns one option letter. Served on Together's platform; recipe published.
Decides
choice, score, noul, classify, route
choice, classify, route
Architecture
rizzo-flow
tev
Fine-tuned from
xhtoken/spark-x2.5-4b
qwen/qwen3.5-4b
License
apache-2.0
Unspecified — weights licence being finalised
Availability
Open weights
Open weights + hosted API
Hosted by
—
Together AI
Input price
—
$0.042/MTok
Decision accuracy
64.8%
88.0%
Calibration error
0.112
—
Valid action rate
—
—
Median latency
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 rizzo-flow and tev1?
rizzo-flow is from Rizzo AI Academy and tev1 from Together AI. rizzo-flow has open weights you can download and run; tev1 has open weights and a hosted API. Both answer choice, classify and route questions. Only rizzo-flow answers score and noul. rizzo-flow is licensed apache-2.0; tev1, other.
Which is more accurate, rizzo-flow or tev1?
They report on different suites — rizzo-flow 64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0, tev1 88.0% on Together development set (reused, not held out) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, rizzo-flow or tev1?
rizzo-flow: Free (open weights). tev1: $0.042 / $0 per 1M, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run rizzo-flow or tev1 locally?
Yes, both: systemone pull rizzo-ai-academy/rizzo-flow and systemone pull together-ai/tev1 download the weights.
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
